© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 193419
    Prev
    Next
    INDEX
    Explanations

    **action: examples**

    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_27_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
    傚
    0.43
    每月
    0.40
    剂量
    0.38
     Geometry
    0.37
     אטאטורק
    0.37
     ການ
    0.37
     আনোয়ার
    0.37
     مداخل
    0.36
    щення
    0.36
     Cyr
    0.36
    POSITIVE LOGITS
    .!
    0.44
    !।
    0.40
    %!
    0.39
    urón
    0.38
    !
    0.37
     locked
    0.37
     गोनी
    0.37
    within
    0.36
     거리
    0.36
    zon
    0.36
    Activations Density 0.001%

    No Known Activations