© 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-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26646
    Prev
    Next
    INDEX
    Explanations

    years or specific numbers

    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
    s
    2.06
    t
    2.02
    r
    1.68
    म
    1.22
    ิ
    1.20
    u
    1.18
    <0x0D>
    1.14
    d
    1.13
    v
    1.12
    ים
    1.09
    POSITIVE LOGITS
    一些
    1.10
     oxid
    1.09
     as
    1.08
    क्राइब
    1.07
     a
    1.03
    .。
    1.01
    西
    0.95
    শংস
    0.94
     يع
    0.93
    urized
    0.90
    Activations Density 0.038%

    No Known Activations