© 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. 13805
    Prev
    Next
    INDEX
    Explanations

    code snippets, particularly C/C++ and Java, including keywords, standard library functions, and code-related jargon

    oai_token-act-pair · gemini-2.0-flash

    technical identifiers or attributes

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

    )

    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
    ~
    -0.54
    <strong>
    -0.54
    0
    -0.54
    1
    -0.54
    <em>
    -0.53
    2
    -0.50
    [
    -0.49
    %
    -0.49
    !
    -0.48
    (!
    -0.47
    POSITIVE LOGITS
    featureID
    1.31
     متعلقه
    1.30
    SourceChecksum
    1.25
     ModelExpression
    1.20
    ThroughAttribute
    1.16
     utafitiHapana
    1.14
    parsedMessage
    1.12
     חיצוניים
    1.10
    abestanden
    1.09
     initComponents
    1.07
    Activations Density 10.433%

    No Known Activations