© 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. 3405
    Prev
    Next
    INDEX
    Explanations

    code snippets, programming terms, and platform names.

    oai_token-act-pair · gemini-2.0-flash

    technical terms related to programming and system commands

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

    Code and computer content

    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
    '];
    -0.98
    ");
    -0.94
    ');
    -0.93
     */
    -0.93
    ";
    -0.92
    ")]
    -0.91
    '])){
    -0.90
    '},
    -0.89
     \
    -0.86
    ';
    -0.85
    POSITIVE LOGITS
    ↵
    2.28
    ‚¬
    0.38
    ึ
    0.37
    TagMode
    0.36
    ěry
    0.33
    webElementGuid
    0.33
    merate
    0.32
    mpeg
    0.32
    postmedia
    0.31
    章节错误
    0.31
    Activations Density 20.136%

    No Known Activations