© 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. 2717
    Prev
    Next
    INDEX
    Explanations

    programming terms

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

    code syntax, including keywords like public, static, class, override, protected, const and the symbols [ ], <, >, ; , namespace, etc

    oai_token-act-pair · gemini-2.0-flash

    code

    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
    max
    -0.59
     ExecuteAsync
    -0.59
    go
    -0.56
    form
    -0.55
    top
    -0.54
     arşivlendi
    -0.50
    usión
    -0.49
     niv
    -0.49
     Exacts
    -0.49
     balancer
    -0.49
    POSITIVE LOGITS
    MigrationBuilder
    0.66
    GeneratedCode
    0.60
    cyjna
    0.56
    ocide
    0.56
    Einzelnachweise
    0.56
     кӀ
    0.56
    gnition
    0.56
    brigens
    0.53
    tować
    0.53
    jandra
    0.52
    Activations Density 0.230%

    No Known Activations