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. 16350
    Prev
    Next
    INDEX
    Explanations

    substrings resembling publication references that follow the format volume-page

    oai_token-act-pair · gemini-2.0-flash

    research publications

    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
    principalTable
    -0.82
     unknownFields
    -0.81
    RegressionTest
    -0.71
    Географи
    -0.68
     leaſt
    -0.67
     Numerade
    -0.65
     jsPsych
    -0.65
    WithIOException
    -0.65
     itſelf
    -0.61
    webElementXpaths
    -0.60
    POSITIVE LOGITS
     BitmapFactory
    0.48
    ariu
    0.48
    ARI
    0.47
    providedIn
    0.46
    FieldBuilder
    0.45
     xs
    0.45
    ivoli
    0.44
    BuildContext
    0.44
    ItemView
    0.44
     SqlParameter
    0.43
    Activations Density 1.614%

    No Known Activations