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. 1697
    Prev
    Next
    INDEX
    Explanations

    names of people in legal documents, historical texts, and family history records

    oai_token-act-pair · gemini-2.0-flash

    Names

    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
     Sancho
    -0.57
     trumpets
    -0.57
     crests
    -0.56
     shroud
    -0.56
     shrou
    -0.56
     goggles
    -0.55
     picket
    -0.55
     cardinals
    -0.54
     camels
    -0.54
     OLS
    -0.54
    POSITIVE LOGITS
     Administrativna
    0.64
     للاسماء
    0.61
    存于互联网档案馆
    0.56
    //</
    0.56
     referrerpolicy
    0.54
     مشين
    0.53
     resourceCulture
    0.52
    ina
    0.52
    hver
    0.51
    ana
    0.50
    Activations Density 17.145%

    No Known Activations