© 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. 19317
    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
     decks
    0.38
    さえ
    0.34
    muster
    0.33
    dwyd
    0.32
    నాన్ని
    0.32
     व्यक्तियों
    0.31
     অভাব
    0.31
     الداله
    0.31
    ﺯ
    0.31
    פתח
    0.31
    POSITIVE LOGITS
     cases
    2.16
     caso
    1.84
     Cases
    1.82
    Cases
    1.81
     случаев
    1.81
    cases
    1.80
     случае
    1.73
     случаи
    1.73
     casos
    1.70
     kasus
    1.67
    Activations Density 0.240%

    No Known Activations