© 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. 235779
    Prev
    Next
    INDEX
    Explanations

    explanationorganization, numbers, abbreviations, and specific terms

    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
    겐
    0.44
    眠
    0.38
    צר
    0.33
    Cher
    0.32
     tummy
    0.32
     Schub
    0.32
    进口
    0.32
    ంచ
    0.32
    듈
    0.32
    엄
    0.31
    POSITIVE LOGITS
     Almost
    0.46
     vigorously
    0.46
     સ્ક
    0.44
     Absolutely
    0.43
     теперь
    0.43
     presiding
    0.42
     reluctantly
    0.42
     expected
    0.42
     अब
    0.42
     लगभग
    0.41
    Activations Density 0.000%

    No Known Activations