© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31836
    Prev
    Next
    INDEX
    Explanations

    "Yunnan" "W"

    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_50_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
     disc
    0.43
    惰
    0.39
     Lorenz
    0.37
    ORES
    0.35
    Pittsburgh
    0.35
     БД
    0.35
     meas
    0.34
     দ্ব
    0.34
    Disc
    0.34
    ignez
    0.34
    POSITIVE LOGITS
     W
    0.64
     ال
    0.56
     Mang
    0.48
    Mang
    0.47
     डब्ल्यू
    0.45
     L
    0.43
    Cole
    0.43
     Wam
    0.41
    mang
    0.40
    uro
    0.39
    Activations Density 0.002%

    No Known Activations