© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12182
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to cooking and recipes

    oai_token-act-pair · gemini-2.0-flash

    golf

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     recipe
    -1.59
     recipes
    -1.50
     Recipe
    -1.45
    recipe
    -1.39
    Recipe
    -1.34
     Equation
    -1.32
     RECIPE
    -1.29
     equation
    -1.28
     Recipes
    -1.27
    Recipes
    -1.26
    POSITIVE LOGITS
     golf
    1.23
     Golf
    1.17
    golf
    1.09
    Golf
    1.06
     GOLF
    0.98
     golfing
    0.89
    GOLF
    0.85
     golfers
    0.81
     golfer
    0.79
    ゴルフ
    0.66
    Activations Density 2.341%

    No Known Activations