© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 200312
    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_6_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
    ↵
    0.84
    .
    0.67
    られない
    0.62
    脂肪
    0.60
    ந்தை
    0.58
     می‌تواند
    0.57
     grueling
    0.56
    祝
    0.56
    elope
    0.55
     불구하고
    0.55
    POSITIVE LOGITS
    to
    1.36
    ক
    1.34
     to
    1.13
    та
    1.03
    n
    1.02
    م
    1.01
    ن
    0.96
    Ii
    0.95
    ك
    0.93
    is
    0.93
    Activations Density 0.000%

    No Known Activations