© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 137294
    Prev
    Next
    INDEX
    Explanations

    SQL table commands

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    หรือ
    0.63
     or
    0.55
     или
    0.55
     eller
    0.51
    或
    0.51
     hoặc
    0.50
     alebo
    0.49
     oder
    0.48
     ຫຼື
    0.47
    Or
    0.47
    POSITIVE LOGITS
     bluish
    0.39
     ske
    0.37
     Ske
    0.37
     Knot
    0.37
     skeletal
    0.37
     vandal
    0.36
    靑
    0.36
     Tsai
    0.36
    景
    0.36
     Kaw
    0.36
    Activations Density 0.001%

    No Known Activations