© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10043
    Prev
    Next
    INDEX
    Explanations

    legal citations or references to time

    oai_token-act-pair · gemini-2.0-flash

    S and/or colon character

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    7
    -0.56
    3
    -0.54
    ral
    -0.52
     attendre
    -0.52
    vii
    -0.50
     względu
    -0.50
     essayer
    -0.49
     bridges
    -0.49
     Drei
    -0.49
     réparer
    -0.48
    POSITIVE LOGITS
    AndEndTag
    0.96
    awtextra
    0.96
     ویکی‌پدیای
    0.89
    WithIOException
    0.86
     AssemblyCulture
    0.85
    ₀
    0.83
    ⁰
    0.80
     Kork
    0.77
     estekak
    0.77
     Maren
    0.77
    Activations Density 9.229%

    No Known Activations