© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 138030
    Prev
    Next
    INDEX
    Explanations

    shoulder

    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_46_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
    뱀
    0.40
     dors
    0.39
    InteropServices
    0.39
     winged
    0.38
    Ivy
    0.38
     wing
    0.37
    Wing
    0.37
     Dorothe
    0.37
     পারছেন
    0.36
     wings
    0.36
    POSITIVE LOGITS
     shoulder
    1.54
     Shoulder
    1.42
    肩
    1.24
    shoulder
    1.21
     shoulders
    1.09
     肩
    1.05
    ショルダー
    0.96
     ショルダー
    0.89
     épaules
    0.88
     कंधे
    0.88
    Activations Density 0.012%

    No Known Activations