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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 6035
    Prev
    Next
    INDEX
    Explanations

    references to figures or tables inside a document

    oai_token-act-pair · gemini-2.0-flash

    references to figures and examples

    np_token-act-pair-logits · gpt-4o-mini

    figure and related code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/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
     in
    -0.63
     In
    -0.46
    SpringRunner
    -0.45
     referrerpolicy
    -0.43
    endregion
    -0.43
    DOCTYPE
    -0.41
    ()]);
    -0.40
    ướ
    -0.40
     which
    -0.38
     cui
    -0.38
    POSITIVE LOGITS
    \{\\
    0.89
    DockStyle
    0.73
     виправивши
    0.72
     figure
    0.70
    ViewImports
    0.69
     propOrder
    0.69
    ContentAsync
    0.68
    ItemBackground
    0.68
    الدراسه
    0.67
    expandindo
    0.66
    Activations Density 5.966%

    No Known Activations