© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3404
    Prev
    Next
    INDEX
    Explanations

    words related to food preparation and dining

    oai_token-act-pair · gemini-2.0-flash

    words related to food and culinary activities

    np_token-act-pair-logits · gpt-4o-mini

    eating or food

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    出版年
    -0.56
     fallu
    -0.48
     réaliste
    -0.45
     bông
    -0.45
    ⇝
    -0.44
    bootstrapcdn
    -0.44
    fwrite
    -0.43
    heureusement
    -0.43
     getWidth
    -0.42
    Véxase
    -0.42
    POSITIVE LOGITS
     eating
    1.45
     food
    1.43
     culinary
    1.40
     eat
    1.38
     cuisine
    1.35
    Eating
    1.33
     Eating
    1.32
     foods
    1.30
     Food
    1.28
    Food
    1.27
    Activations Density 11.696%

    No Known Activations