© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1697
    Prev
    Next
    INDEX
    Explanations

    uses notation common in mathematical texts.

    oai_token-act-pair · gemini-2.0-flash

    programming-related terms or identifiers

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

    Let

    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
    Negative Logits
    ']))
    -0.63
    '])
    -0.62
    "])
    -0.61
    [];
    -0.61
    []
    -0.61
    `;
    -0.60
    Xna
    -0.59
    ("")]
    -0.59
    )");
    -0.59
    //};
    -0.58
    POSITIVE LOGITS
    writeField
    0.62
     us
    0.59
    unknownFields
    0.49
    AndEndTag
    0.48
     comigo
    0.47
     me
    0.47
     meille
    0.47
    unicaciones
    0.47
    WebVitals
    0.46
    readString
    0.46
    Activations Density 5.369%

    No Known Activations