© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3834
    Prev
    Next
    INDEX
    Explanations

    text from a program bug tracker

    oai_token-act-pair · gemini-2.0-flash

    terms related to debugging or error reporting

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

    Technical Documentation

    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
    责任编辑
    -0.50
     editing
    -0.47
     ویکی‌پدیا
    -0.46
    selections
    -0.45
     settle
    -0.44
     Bluestacks
    -0.44
     inflater
    -0.43
     Doy
    -0.43
    principalColumn
    -0.43
     Humanos
    -0.42
    POSITIVE LOGITS
    :✨
    0.76
    ftagPool
    0.71
    rungsseite
    0.66
    MigrationBuilder
    0.66
     privée
    0.60
    oneofs
    0.58
    addCriterion
    0.57
    ANTLR
    0.56
     imageNamed
    0.53
     térm
    0.52
    Activations Density 6.004%

    No Known Activations