© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 163573
    Prev
    Next
    INDEX
    Explanations

    Rarity and clothing or textiles

    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_13_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
    که
    0.54
    나
    0.46
    isce
    0.44
    کی
    0.44
    म
    0.42
    3
    0.40
     or
    0.40
    ต
    0.40
    ﺮ
    0.39
     otter
    0.39
    POSITIVE LOGITS
     Textile
    0.63
    👗
    0.61
     Clothing
    0.59
     textile
    0.58
     옷
    0.57
    Clothing
    0.57
    服装
    0.56
     quilts
    0.56
    clothing
    0.56
     платье
    0.55
    Activations Density 0.001%

    No Known Activations