© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14681
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with food preparation and cooking.

    oai_token-act-pair · gemini-2.0-flash

    cooking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     cook
    -1.02
     cooking
    -0.98
     cooks
    -0.85
     Cook
    -0.81
     COOK
    -0.81
     Cooking
    -0.80
     cocinar
    -0.77
    Cook
    -0.76
    cooking
    -0.75
    Cooking
    -0.74
    POSITIVE LOGITS
    liothèque
    0.75
     Roskov
    0.72
    ⓧ
    0.71
    RegressionTest
    0.70
     transférez
    0.69
     nonUne
    0.68
    +#+#
    0.62
     ***!
    0.60
    Personensuche
    0.60
     Photocase
    0.60
    Activations Density 48.005%

    No Known Activations