© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 40728
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
     注
    0.40
     타이
    0.38
     racionais
    0.38
     vivos
    0.38
     Drawings
    0.38
    ccgi
    0.37
     Cálculo
    0.37
     ai
    0.36
     Medicines
    0.35
    icu
    0.34
    POSITIVE LOGITS
    Ing
    0.44
    ేశ
    0.37
     gem
    0.36
     menem
    0.35
    ourd
    0.35
     совсем
    0.34
    戝
    0.34
     Ing
    0.34
    ulang
    0.34
     වෙන
    0.33
    Activations Density 0.000%

    No Known Activations