© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11551
    Prev
    Next
    INDEX
    Explanations

    structured data such as phone numbers, mathematical formulas, programming syntax, and statistical data

    oai_token-act-pair · gemini-2.0-flash

    Code and foreign language snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    tagHelperRunner
    -0.82
    __":
    -0.68
     rozwiąz
    -0.63
    RegressionTest
    -0.61
    CloseOperation
    -0.61
    parsedMessage
    -0.60
    standers
    -0.59
    стема
    -0.59
    ✨:
    -0.57
    dération
    -0.57
    POSITIVE LOGITS
    acyjnych
    0.59
     των
    0.57
    ższych
    0.55
     tych
    0.54
    znych
    0.54
    логических
    0.54
    kových
    0.54
     those
    0.52
     naszych
    0.52
    towych
    0.51
    Activations Density 1.253%

    No Known Activations