© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11556
    Prev
    Next
    INDEX
    Explanations

    foreign language text, particularly Spanish and French

    oai_token-act-pair · gemini-2.0-flash

    multiple languages

    np_max-act-logits · gemini-2.0-flash

    Romance articles/possessives Method used: 1. Reason: tokens like "de, el, mon, una, petite, vieille" are articles/possessive/adjectival function words in Romance languages. Explanation returned: Romance articles/possessives

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.43
     otomatig
    -0.40
    __':
    -0.39
    Personensuche
    -0.39
     utafitiHapana
    -0.39
    
    -0.38
     rhestr
    -0.38
     مرئيه
    -0.37
    arschijnlijk
    -0.36
    ConstraintMaker
    -0.35
    POSITIVE LOGITS
     tiroirs
    0.79
     lèvres
    0.79
     maternidade
    0.77
     oreilles
    0.77
     épaules
    0.76
     nuages
    0.74
     occhiali
    0.73
     cappello
    0.72
     jouets
    0.71
     oração
    0.71
    Activations Density 0.803%

    No Known Activations