© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 148377
    Prev
    Next
    INDEX
    Explanations

    ordering lists

    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_23_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
     Horn
    0.40
     \
    0.39
     N
    0.39
     niem
    0.38
     لان
    0.37
     nav
    0.37
     ο
    0.36
     ஏனெனில்
    0.36
     Accom
    0.36
     ক্যাথ
    0.36
    POSITIVE LOGITS
    ántica
    0.42
    antique
    0.40
     errores
    0.40
    टीशन
    0.39
    aphazard
    0.39
     ошибки
    0.39
     ошиб
    0.38
    XmlElement
    0.38
     библиотека
    0.38
    𐰢
    0.38
    Activations Density 0.034%

    No Known Activations