© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 6199
    Prev
    Next
    INDEX
    Explanations

    tandfonline.com/doi/

    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_38_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
     verb
    0.45
    鏻
    0.42
     GRAD
    0.41
     Ceylon
    0.41
     Verb
    0.39
    ಜ್ಞ
    0.39
    鰭
    0.39
    जिस्ट
    0.38
     mouvements
    0.37
    引进
    0.37
    POSITIVE LOGITS
    mii
    0.39
    UQ
    0.36
    钰
    0.35
    Qualifier
    0.35
    逗
    0.35
     physically
    0.34
    checked
    0.34
     Quint
    0.34
    arendon
    0.34
    waitSeconds
    0.33
    Activations Density 0.000%

    No Known Activations