© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14343
    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_40_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
     PU
    0.37
     Polk
    0.36
    સાય
    0.36
    adda
    0.36
     kall
    0.36
    ligt
    0.36
     Zak
    0.34
    சிக்க
    0.34
    阎
    0.34
    тия
    0.33
    POSITIVE LOGITS
     goog
    0.48
    sear
    0.47
     வீடியோ
    0.46
     검색
    0.46
    視頻
    0.46
    検索
    0.45
     google
    0.44
     vidéos
    0.43
    searching
    0.42
     videos
    0.42
    Activations Density 0.000%

    No Known Activations