Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1677
    Prev
    Next
    INDEX
    Explanations

    hyphens and other punctuation within words or phrases

    oai_token-act-pair · gemini-2.0-flash

    -

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    on
    -0.98
    like
    -0.95
    parsedMessage
    -0.90
     Signalez
    -0.79
    one
    -0.78
    only
    -0.76
    ones
    -0.76
    less
    -0.73
    IsContent
    -0.73
    rrggbb
    -0.72
    POSITIVE LOGITS
    er
    0.65
    erman
    0.61
    ers
    0.53
    retrieve
    0.50
    textsc
    0.49
    viate
    0.47
    ournal
    0.47
     NDEBUG
    0.47
    gine
    0.46
    ER
    0.45
    Activations Density 11.671%

    No Known Activations