© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33261
    Prev
    Next
    INDEX
    Explanations

    pathway datasets import

    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_3_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
    的就是
    0.76
    ו
    0.66
    ın
    0.63
    お客様
    0.62
    u
    0.62
    一块
    0.57
    お店
    0.55
    are
    0.55
    了这个
    0.54
    了自己的
    0.53
    POSITIVE LOGITS
    ن
    1.03
    ال
    0.76
    مس
    0.71
    ン
    0.71
    می
    0.70
     ülke
    0.70
    UT
    0.67
    ರ್
    0.66
     África
    0.66
     étrang
    0.65
    Activations Density 0.000%

    No Known Activations