© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 51839
    Prev
    Next
    INDEX
    Explanations

    IlluminateFacades Regulation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_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
     intercambio
    0.67
    asjoner
    0.63
     advogado
    0.61
    ā
    0.60
    on
    0.60
     potrebbero
    0.60
     amistad
    0.60
    Ｂ
    0.59
     ойнойт
    0.58
     অভিব্যক্তি
    0.58
    POSITIVE LOGITS
    ↵↵
    0.79
     stehen
    0.56
    天的
    0.53
    راض
    0.52
     prostit
    0.49
    ᅪ
    0.49
    テム
    0.49
     renormal
    0.49
     that
    0.48
     يعني
    0.48
    Activations Density 0.000%

    No Known Activations