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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 2-GEMMASCOPE-TRANSCODER-16K
    4. 14201
    Prev
    Next
    INDEX
    Explanations

    XML-like tags and attributes

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_2/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
    <blockquote>
    -1.80
     myſelf
    -1.09
     Efq
    -1.02
     uſed
    -0.98
     raiſ
    -0.94
    bibfield
    -0.93
     purpoſe
    -0.92
     themſelves
    -0.88
     RIPRODUZIONE
    -0.88
     Jefus
    -0.88
    POSITIVE LOGITS
    ↵
    0.56
    <eos>
    0.50
    <h2>
    0.48
    '
    0.45
    </th>
    0.45
    .)
    0.45
    ."
    0.45
    ={{
    0.45
    </h2>
    0.44
    ↵↵
    0.44
    Activations Density 0.094%

    No Known Activations