© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 96535
    Prev
    Next
    INDEX
    Explanations

    exchange, trade, swap

    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_14_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    الحضور
    0.14
     constitue
    0.14
    ÍT
    0.14
    %，
    0.14
     సామ
    0.14
     capacités
    0.13
    orragie
    0.13
     sanguí
    0.13
    %);
    0.13
     ଦ
    0.13
    POSITIVE LOGITS
     exchanges
    0.15
     Exchanges
    0.15
     exchange
    0.15
     swaps
    0.15
     Exchange
    0.14
     Swap
    0.13
     کرل
    0.13
    Exchange
    0.13
     Tua
    0.13
    uas
    0.13
    Activations Density 0.008%

    No Known Activations