© 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. 10466
    Prev
    Next
    INDEX
    Explanations

    long sequences of digits and symbols

    oai_token-act-pair · gemini-2.0-flash

    numerical data and metrics

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

    Numbers

    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
    CppMethod
    -0.87
    mybatisplus
    -0.80
    rrggbb
    -0.76
     boucles
    -0.75
    WriteBarrier
    -0.75
    BufferException
    -0.73
     StatefulWidget
    -0.71
     ویکی‌پدیا
    -0.71
     vectorielle
    -0.71
    يكب
    -0.69
    POSITIVE LOGITS
     total
    0.45
     pen
    0.43
     &
    0.43
    am
    0.43
     attendees
    0.41
    /
    0.41
     likes
    0.38
    治
    0.38
    kb
    0.38
    px
    0.38
    Activations Density 4.268%

    No Known Activations