© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 212956
    Prev
    Next
    INDEX
    Explanations

    algebra, non-commutative algebra

    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_16_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
    delà
    0.46
    受益
    0.45
     высокая
    0.44
     Boosting
    0.43
     Bắc
    0.43
    ttemberg
    0.43
    рын
    0.42
    क्षिप्त
    0.42
    쩔
    0.42
    T
    0.42
    POSITIVE LOGITS
     indicate
    0.57
     আপনি
    0.56
     You
    0.55
     you
    0.54
    You
    0.51
    you
    0.49
     friendships
    0.48
     involve
    0.48
     ald
    0.48
     należy
    0.47
    Activations Density 0.000%

    No Known Activations