© 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. 7282
    Prev
    Next
    INDEX
    Explanations

    words and phrases that are frequently used in French-language online technical support forums, including greetings, requests for help, and technical terms

    oai_token-act-pair · gemini-2.0-flash

    French text

    np_max-act-logits · gemini-2.0-flash

    un

    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
    ValueStyle
    -0.83
     nakalista
    -0.75
    Izvori
    -0.70
    writeField
    -0.64
     SafeMath
    -0.63
    basicConfig
    -0.63
     stället
    -0.61
    __(/*!
    -0.59
    AndEndTag
    -0.58
    nologue
    -0.58
    POSITIVE LOGITS
     boîtier
    0.57
    HomeAsUpEnabled
    0.53
     médicament
    0.52
     hébergement
    0.50
     emballage
    0.49
    مدر
    0.49
     investissement
    0.49
     formulaire
    0.49
     réglage
    0.49
    ("~/
    0.49
    Activations Density 0.685%

    No Known Activations