© 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. 2013
    Prev
    Next
    INDEX
    Explanations

    recipes and restaurant reviews.

    oai_token-act-pair · gemini-2.0-flash

    technical programming terms

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

    Food and flavors

    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
     eating
    -0.52
     eat
    -0.48
    Eating
    -0.47
    膳
    -0.46
     dining
    -0.46
    例文帳に追加
    -0.46
     Dining
    -0.45
    eat
    -0.45
    eating
    -0.45
     comedor
    -0.45
    POSITIVE LOGITS
    tagHelperRunner
    0.93
    AsUp
    0.88
     propOrder
    0.85
     cherchés
    0.75
     متعلقه
    0.73
    PerformLayout
    0.73
     Infórmanos
    0.72
    ="@+
    0.69
    EndContext
    0.69
    ftagPool
    0.69
    Activations Density 1.286%

    No Known Activations