© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66880
    Prev
    Next
    INDEX
    Explanations

    shoulder-width apart

    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_41_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
     Chrome
    1.31
    Chrome
    1.17
     chrome
    1.16
    chrome
    0.97
     chromed
    0.93
    Chrom
    0.91
    铬
    0.86
     Chrom
    0.86
     Chromium
    0.84
     chromium
    0.82
    POSITIVE LOGITS
     shoulder
    0.95
     Shoulder
    0.88
    shoulder
    0.82
    肩
    0.82
     shoulders
    0.66
     कंधे
    0.66
     socially
    0.55
     肩
    0.53
    肩膀
    0.52
     hip
    0.50
    Activations Density 0.024%

    No Known Activations