© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 47993
    Prev
    Next
    INDEX
    Explanations

    ./booksbrainprivacymonetizationaihong kong news

    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_31_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
     Kxd
    0.38
     Brian
    0.37
     BANKS
    0.36
     pint
    0.35
     hechas
    0.35
     Edward
    0.35
    瘓
    0.34
     War
    0.33
     Glossary
    0.33
     swing
    0.33
    POSITIVE LOGITS
    nextSend
    0.41
    仡
    0.40
    里程
    0.40
    íl
    0.40
    drav
    0.39
    itemView
    0.38
    ங்கோ
    0.38
    Ná
    0.38
    Circular
    0.38
     প্রেস
    0.37
    Activations Density 0.000%

    No Known Activations