© 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. 46375
    Prev
    Next
    INDEX
    Explanations

    SELECT * FROM

    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
     کئے
    0.44
     forcibly
    0.43
     forcefully
    0.39
     منسل
    0.38
     lonely
    0.38
    _\
    0.38
    reur
    0.38
     अवशेष
    0.38
    ीकरण
    0.37
    豌
    0.37
    POSITIVE LOGITS
    녕하세요
    0.45
    lingen
    0.41
     Brokers
    0.39
    電動
    0.38
    భవ
    0.38
    terne
    0.38
    ضبط
    0.38
    rc
    0.37
     ligt
    0.37
     castings
    0.37
    Activations Density 0.002%

    No Known Activations