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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 16-GEMMASCOPE-TRANSCODER-16K
    4. 16273
    Prev
    Next
    INDEX
    Explanations

    blog posts reviews

    oai_token-act-pair · gemini-2.0-flash

    Review/Blog content

    np_token-act-pair-logits · gemini-2.0-flash

    book reviews and blogs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_16/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
     ProtoMessage
    -0.71
    -------------</
    -0.63
    parsedMessage
    -0.62
     Baillargeon
    -0.62
     AssemblyCulture
    -0.61
    FunctionFlags
    -0.60
    ContentValues
    -0.58
    jsxFileName
    -0.57
     doInBackground
    -0.55
    +#+#
    -0.55
    POSITIVE LOGITS
    ')")
    0.57
    metis
    0.54
     ITIS
    0.53
    wohner
    0.49
     taxes
    0.49
    }`).
    0.48
     fame
    0.48
     venden
    0.48
     للاسماء
    0.48
    )");
    0.47
    Activations Density 1.633%

    No Known Activations