© 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. 15031
    Prev
    Next
    INDEX
    Explanations

    cooking recipe instructions

    oai_token-act-pair · gemini-2.0-flash

    cooked food

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

    cooking/recipes

    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
    OGND
    -0.71
     Shakspeare
    -0.61
    migrationBuilder
    -0.61
    WebVitals
    -0.61
    ^(@)
    -0.59
     Vaticano
    -0.58
     fevere
    -0.58
     wireType
    -0.57
     Solano
    -0.57
     cowl
    -0.57
    POSITIVE LOGITS
     cooked
    0.59
    참고
    0.51
    ArrowToggle
    0.48
    cooked
    0.46
    eleste
    0.45
    transQ
    0.43
     pl
    0.42
    طار
    0.41
    appé
    0.41
    Thunk
    0.41
    Activations Density 1.197%

    No Known Activations