© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 15076
    Prev
    Next
    INDEX
    Explanations

    list and quick sort

    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_13_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
     facteurs
    0.60
     toate
    0.55
     fattori
    0.55
    ktCap
    0.55
     acolo
    0.54
    琕
    0.54
    ﺔ
    0.54
     factores
    0.53
     هناك
    0.53
     fatores
    0.52
    POSITIVE LOGITS
     시작
    0.57
     Chadwick
    0.53
    食用
    0.52
    蔥
    0.52
    mıştı
    0.52
     northeastern
    0.51
     commonwealth
    0.50
    عمل
    0.49
    つき
    0.49
     এসেছিলেন
    0.49
    Activations Density 0.009%

    No Known Activations