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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 16313
    Prev
    Next
    INDEX
    Explanations

    names of people and their titles

    oai_token-act-pair · gemini-2.0-flash

    News and Annoucements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/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
     P
    -0.39
     a
    -0.38
     depan
    -0.38
    不易
    -0.38
     
    -0.37
    ELESS
    -0.36
     no
    -0.35
    빼
    -0.35
     E
    -0.35
     уста
    -0.34
    POSITIVE LOGITS
    DockStyle
    0.97
    InitVars
    0.96
     AssemblyCulture
    0.94
     للمعارف
    0.92
    MigrationBuilder
    0.90
     nahilalakip
    0.88
     CreateTagHelper
    0.88
     препратки
    0.88
    évaluateur
    0.86
    IntoConstraints
    0.85
    Activations Density 0.835%

    No Known Activations