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. 1640
    Prev
    Next
    INDEX
    Explanations

    preformatted code blocks and questions

    oai_token-act-pair · gemini-2.0-flash

    unusual punctuation marks

    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
     We
    -0.75
     It
    -0.69
     But
    -0.64
     You
    -0.64
     In
    -0.61
     As
    -0.60
     If
    -0.59
     He
    -0.59
     This
    -0.58
     At
    -0.57
    POSITIVE LOGITS
     
    0.74
     
    0.68
     ***/
    0.67
     
    0.65
    .)}
    0.63
     ―――――
    0.63
     ་་
    0.63
    ?」
    0.62
    .")]
    0.61
     */}
    0.61
    Activations Density 6.850%

    No Known Activations