© 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. 96506
    Prev
    Next
    INDEX
    Explanations

    cordially invited

    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
     হিসেবে
    0.54
     she
    0.52
     as
    0.50
    ‌
    0.47
     *
    0.45
    ক
    0.45
     und
    0.45
     needed
    0.45
     plotted
    0.45
     subsidized
    0.45
    POSITIVE LOGITS
     ሜ
    0.60
     resumo
    0.52
     procedimento
    0.47
    MsgCallBack
    0.47
    PN
    0.47
     benutzen
    0.47
    ম্ত
    0.47
    ूटूथ
    0.46
     vzduchu
    0.46
     PN
    0.46
    Activations Density 0.000%

    No Known Activations