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. 14103
    Prev
    Next
    INDEX
    Explanations

    Japanese cuisine, especially in a set meal or including mochi

    oai_token-act-pair · gemini-2.0-flash

    rice

    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
     الحره
    -0.71
     referenties
    -0.70
    TemporalType
    -0.65
    HandlerContext
    -0.65
    {{/
    -0.61
    DebuggerNonUser
    -0.56
    ="?
    -0.55
     GeoNames
    -0.54
    存于互联网档案馆
    -0.54
    ********/
    -0.54
    POSITIVE LOGITS
     Rice
    0.68
     grain
    0.68
    rice
    0.67
     rice
    0.65
    Rice
    0.63
     Grain
    0.59
    Grain
    0.56
     Grains
    0.54
     RICE
    0.54
    grain
    0.54
    Activations Density 1.220%

    No Known Activations