© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7506
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands

    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_39_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
     ಏ
    0.43
     Binding
    0.38
     ві
    0.36
     கோயில
    0.36
     وانت
    0.36
     binding
    0.35
     Volume
    0.35
    attachment
    0.35
    èles
    0.34
     കാഴ്ച
    0.34
    POSITIVE LOGITS
    こんにちは
    0.39
     鳥
    0.37
    Gm
    0.37
     rail
    0.35
    parsed
    0.35
     unavoid
    0.34
    BinaryOperation
    0.34
     remed
    0.33
    cend
    0.33
     интеллектуа
    0.33
    Activations Density 0.003%

    No Known Activations