© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12928
    Prev
    Next
    INDEX
    Explanations

    tokens which equal restaurant, or contextually related words such as waiter, waitress, dine and kitchen

    oai_token-act-pair · gemini-2.0-flash

    restaurant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     restaurant
    -1.98
     Restaurant
    -1.66
    Restaurant
    -1.64
    restaurant
    -1.64
     restaurants
    -1.59
     restaurante
    -1.48
     RESTAURANT
    -1.48
     Restaurants
    -1.45
    Restaurants
    -1.31
     restaurantes
    -1.30
    POSITIVE LOGITS
    ValueStyle
    0.77
    %";
    0.63
    RefreshLayout
    0.63
    hyrchwyd
    0.63
     */;
    0.62
    writeFieldEnd
    0.62
    --*/
    0.62
     transfieras
    0.61
    InputBorder
    0.60
     CreateTagHelper
    0.59
    Activations Density 0.030%

    No Known Activations