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. 1689
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical place names in Ireland and Scotland

    oai_token-act-pair · gemini-2.0-flash

    locations

    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
     <>",
    -0.78
    TypedDataSet
    -0.76
    SourceChecksum
    -0.73
     '{@
    -0.73
    msgTypes
    -0.71
     nakalista
    -0.70
     jLabel
    -0.69
    ManagedBean
    -0.69
    rawDesc
    -0.69
    migrationBuilder
    -0.68
    POSITIVE LOGITS
    IntoConstraints
    0.48
     Stead
    0.41
     Steel
    0.40
    reactstrap
    0.40
     Blues
    0.40
     lampe
    0.39
     sred
    0.39
     Steele
    0.38
    خر
    0.38
    ssf
    0.38
    Activations Density 2.004%

    No Known Activations