© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 47203
    Prev
    Next
    INDEX
    Explanations

    Anderson, Cell, War

    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_13_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
    ین
    0.62
    제목
    0.57
    ос
    0.55
    ﻔ
    0.55
    %}
    0.52
    증
    0.50
    וס
    0.50
    취
    0.50
    eyen
    0.48
    خط
    0.48
    POSITIVE LOGITS
     unanticipated
    0.64
     SVM
    0.61
     edema
    0.56
     EPIC
    0.56
     सोया
    0.54
     ADA
    0.54
     Rusty
    0.54
     HAVING
    0.54
     steak
    0.53
     almond
    0.53
    Activations Density 0.000%

    No Known Activations