© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 62686
    Prev
    Next
    INDEX
    Explanations

    ส่วนหนึ่ง

    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_2_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
    Š
    1.18
    U
    1.11
    AMENTO
    1.10
    У
    1.10
    İ
    1.09
    Č
    1.06
    O
    1.02
    Vý
    1.01
    అ
    1.01
    어
    0.98
    POSITIVE LOGITS
    r
    1.52
    ر
    1.41
    t
    1.38
    of
    1.37
    -
    1.29
    تها
    1.27
    that
    1.23
    mation
    1.21
    л
    1.19
    ях
    1.17
    Activations Density 0.000%

    No Known Activations