© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78265
    Prev
    Next
    INDEX
    Explanations

    python decorator

    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_0_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
    ش
    2.45
    การ
    1.87
    ne
    1.66
    ai
    1.60
    م
    1.55
    ek
    1.54
    ช่วง
    1.52
    기
    1.50
    to
    1.48
    ب
    1.44
    POSITIVE LOGITS
    ț
    1.37
    يس
    1.23
    ьте
    1.17
    كي
    1.16
     Consultado
    1.16
    햐
    1.16
    كمال
    1.13
    ة
    1.13
    нии
    1.12
    ней
    1.11
    Activations Density 0.000%

    No Known Activations