© 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-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 30095
    Prev
    Next
    INDEX
    Explanations

    doubling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    H
    0.19
    a
    0.18
    К
    0.18
    d
    0.18
     légère
    0.17
    y
    0.17
    b
    0.17
    У
    0.17
    e
    0.16
    B
    0.16
    POSITIVE LOGITS
    (
    0.20
    ן
    0.16
     nowych
    0.15
    </h1>
    0.13
    '},
    0.13
    ilingual
    0.13
    ัติ
    0.13
    赢得
    0.13
    ढ़
    0.12
    ح
    0.12
    Activations Density 0.013%

    No Known Activations