© 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. 2407
    Prev
    Next
    INDEX
    Explanations

    angle brackets, code syntax, and related programming terms.

    oai_token-act-pair · gemini-2.0-flash

    code-related markup tags

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

    HTML 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
    NUMX
    -0.63
     first
    -0.61
     •
    -0.61
     Réponses
    -0.59
    ?\\
    -0.59
     :\\
    -0.58
    -\\
    -0.57
     fi
    -0.57
    ;\\
    -0.56
    fl
    -0.54
    POSITIVE LOGITS
    <code>
    1.98
    <i>
    1.68
    <em>
    1.58
     `
    1.30
     
    1.15
    <u>
    1.11
     {@
    1.00
    <sub>
    0.95
    <sup>
    0.90
     ${\
    0.88
    Activations Density 4.164%

    No Known Activations