© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 954
    Prev
    Next
    INDEX
    Explanations

    words and names from certain Polynesian languages, technical language about pressing or molding and some legal terms

    oai_token-act-pair · gemini-2.0-flash

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    noc
    -0.55
    xp
    -0.49
    getC
    -0.46
    xc
    -0.46
    xC
    -0.45
     comp
    -0.44
    ARC
    -0.43
    antic
    -0.42
     VIAF
    -0.42
    ICS
    -0.42
    POSITIVE LOGITS
     Monfieur
    0.66
     ſeveral
    0.64
     المعيارى
    0.62
     Majefty
    0.62
     كومونز
    0.62
     enfans
    0.61
     médicaux
    0.61
     ModelExpression
    0.60
     spéciaux
    0.60
     ſtate
    0.59
    Activations Density 1.767%

    No Known Activations