© 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. 7741
    Prev
    Next
    INDEX
    Explanations

    words related to problem solving, conflict, resolution, and fixing things

    oai_token-act-pair · gemini-2.0-flash

    uses of the term "by"

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

    say "by"

    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
     ProtoMessage
    -0.63
     hindurch
    -0.59
    rån
    -0.55
    MigrationBuilder
    -0.55
    GEBURTS
    -0.55
    expandindo
    -0.54
     tartalomajánló
    -0.54
    الحياه
    -0.54
    cipar
    -0.52
    aarrggbb
    -0.51
    POSITIVE LOGITS
     by
    3.13
     oleh
    2.16
    by
    2.13
     By
    2.08
    By
    1.95
     BY
    1.73
     توسط
    1.55
     ידי
    1.41
     przez
    1.41
     pelos
    1.30
    Activations Density 10.362%

    No Known Activations