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. 1691
    Prev
    Next
    INDEX
    Explanations

    helping verbs and modal verbs

    oai_token-act-pair · 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
    AccessorTable
    -0.60
    /*
    -0.55
    jsxFileName
    -0.52
    :\/\/
    -0.51
    IndentedString
    -0.47
    please
    -0.47
    atola
    -0.46
    otations
    -0.46
     validamos
    -0.46
     beträgt
    -0.46
    POSITIVE LOGITS
    ⓧ
    0.71
    makeText
    0.65
     brought
    0.63
     ModelExpression
    0.62
     bringing
    0.55
    Portail
    0.54
     bring
    0.54
    brought
    0.53
     незавершена
    0.53
    NegativeButton
    0.52
    Activations Density 4.270%

    No Known Activations