© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33342
    Prev
    Next
    INDEX
    Explanations

    magic world, grid, bag, bone

    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_3_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
     ง
    0.77
    ）；
    0.77
    ला
    0.74
    ảo
    0.73
     prerogative
    0.71
     bảng
    0.71
    ч
    0.71
    ）,
    0.70
    ن
    0.70
    ：
    0.70
    POSITIVE LOGITS
    1
    1.03
    t
    1.02
    (
    0.79
    mert
    0.74
    いますが
    0.73
    تان
    0.72
    2
    0.72
    y
    0.71
    6
    0.71
    א
    0.71
    Activations Density 0.028%

    No Known Activations