© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 46538
    Prev
    Next
    INDEX
    Explanations

    Haar Cascade classifiers

    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_22_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
     kota
    0.44
    ້ອ
    0.43
    orphous
    0.42
    不死
    0.41
    棲
    0.40
     mittels
    0.40
    zeniu
    0.39
     Органи
    0.39
     ?-
    0.39
     الخم
    0.39
    POSITIVE LOGITS
     المالية
    0.42
    гава
    0.42
    生意
    0.41
     gubernatorial
    0.39
    ELINE
    0.39
     চেয়েছিলেন
    0.38
    府
    0.38
    ലു
    0.37
     ಚುನಾವಣ
    0.37
     цього
    0.37
    Activations Density 0.002%

    No Known Activations