© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 209614
    Prev
    Next
    INDEX
    Explanations

    warrior, war, warping

    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_5_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
    ك
    1.05
    čiti
    1.02
     약
    1.00
    .
    0.99
    .。
    0.97
     ս
    0.95
    IM
    0.95
     ва
    0.94
    غ
    0.94
     établi
    0.91
    POSITIVE LOGITS
    ى
    1.52
    le
    1.48
    en
    1.39
    m
    1.29
    ע
    1.27
    ции
    1.26
    ే
    1.23
    z
    1.19
    io
    1.18
    ó
    1.16
    Activations Density 0.000%

    No Known Activations