© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 56356
    Prev
    Next
    INDEX
    Explanations

    dividing, split, separate

    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_11_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
    ıları
    0.62
    دی
    0.61
    柇
    0.58
    یده
    0.57
    for
    0.56
    یا
    0.54
    gramModel
    0.54
    rió
    0.53
    իկ
    0.53
    рии
    0.52
    POSITIVE LOGITS
    ال
    0.85
    \
    0.63
     na
    0.63
     Z
    0.61
     W
    0.61
     Erinner
    0.59
    u
    0.59
     H
    0.58
     SCREEN
    0.57
     V
    0.57
    Activations Density 0.000%

    No Known Activations