© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136293
    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_12_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
     conspiring
    0.61
    cdots
    0.54
     Ни
    0.53
     випад
    0.53
    opold
    0.52
     ड
    0.51
    rol
    0.51
     Fur
    0.51
    unud
    0.50
     ద
    0.49
    POSITIVE LOGITS
     বিক্রয়
    0.54
    িট
    0.51
     anns
    0.50
    ContentType
    0.50
     fisheries
    0.49
    IA
    0.49
    סה
    0.49
     shew
    0.48
    ৈধ
    0.48
     toasts
    0.48
    Activations Density 0.000%

    No Known Activations