© 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. 156379
    Prev
    Next
    INDEX
    Explanations

    vista panorámica o espectacular

    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
    Negative Logits
    '
    1.45
    ل
    1.34
     for
    1.30
    ?
    1.28
    ن
    1.20
    i
    1.16
     in
    1.15
    و
    1.13
    ем
    1.13
    在
    1.11
    POSITIVE LOGITS
    는
    1.18
    ской
    1.07
    ની
    0.98
    सन
    0.97
    ON
    0.96
    َت
    0.96
    ز
    0.95
    AN
    0.94
    ین
    0.94
    ς
    0.94
    Activations Density 0.000%

    No Known Activations