© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 235688
    Prev
    Next
    INDEX
    Explanations

    still, soon, reliable

    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_25_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
    лень
    0.41
    䏲
    0.39
    řízení
    0.36
     მიმოწერა
    0.35
     আরা
    0.34
     Кеменов
    0.34
     Reglamento
    0.34
     verdade
    0.33
     или
    0.33
    ▢
    0.33
    POSITIVE LOGITS
     Still
    0.46
    still
    0.41
     still
    0.40
    Still
    0.38
     shame
    0.36
     STILL
    0.36
     absorbs
    0.35
    依然
    0.34
    υγ
    0.34
     arrests
    0.33
    Activations Density 0.000%

    No Known Activations