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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 16362
    Prev
    Next
    INDEX
    Explanations

    references to supporting figures and files, and some bracketed asides with numbers

    oai_token-act-pair · gemini-2.0-flash

    scientific article references

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/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
     ModelExpression
    -0.87
     typelib
    -0.83
     BoxFit
    -0.81
     snippetHide
    -0.79
    PerformLayout
    -0.79
    awtextra
    -0.79
    principalColumn
    -0.79
     فريبيس
    -0.77
    Билгалдахарш
    -0.75
     kasarigan
    -0.74
    POSITIVE LOGITS
    argli
    0.52
    seck
    0.50
    ophanes
    0.49
    وردار
    0.49
    ghua
    0.48
    ultur
    0.48
    rophi
    0.47
    aguya
    0.46
    BaseType
    0.45
    oubted
    0.45
    Activations Density 3.346%

    No Known Activations