© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 15193
    Prev
    Next
    INDEX
    Explanations

    scientific techniques and tools

    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_13_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
    ma
    0.48
     ),
    0.46
    u
    0.45
    UI
    0.45
     ma
    0.45
     contempor
    0.45
    ūd
    0.44
    PD
    0.44
    ”,
    0.44
    in
    0.43
    POSITIVE LOGITS
     Sehen
    0.57
     Меня
    0.53
    gaxModule
    0.50
    栤
    0.49
     ਤਾਂ
    0.49
    znam
    0.48
    ர்
    0.48
    餒
    0.48
    arenko
    0.48
     Crossed
    0.48
    Activations Density 0.093%

    No Known Activations