© 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. 14276
    Prev
    Next
    INDEX
    Explanations

    the word "some" or "one" preceded by "at"

    oai_token-act-pair · gemini-2.0-flash

    specific numerical or coded identifiers

    np_token-act-pair-logits · gpt-4o-mini
    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
     at
    -0.75
    addCriterion
    -0.71
     Reverso
    -0.71
    ValueStyle
    -0.70
    migrationBuilder
    -0.64
    rawDesc
    -0.63
    पया
    -0.60
    PerformLayout
    -0.59
    DeleteBehavior
    -0.58
    ArrowToggle
    -0.56
    POSITIVE LOGITS
    στή
    0.55
    ITHUB
    0.53
     chrétien
    0.51
     numberWith
    0.50
    onyx
    0.49
    âmetro
    0.48
     "-";
    0.48
     blockage
    0.47
    icamente
    0.47
    ariato
    0.46
    Activations Density 0.715%

    No Known Activations