© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38756
    Prev
    Next
    INDEX
    Explanations

    best

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    ంగ్‌
    0.41
     DEAL
    0.41
     HOUR
    0.38
    劧
    0.38
    ैग
    0.37
    detailID
    0.37
     Mendez
    0.37
    േഷ
    0.37
    ﾗ
    0.37
    鰍
    0.37
    POSITIVE LOGITS
     all
    0.72
     tất
    0.63
     все
    0.60
     सभी
    0.57
     semua
    0.55
     wszystkie
    0.55
     kaikki
    0.54
    すべて
    0.53
     vse
    0.53
     جميع
    0.51
    Activations Density 0.014%

    No Known Activations