© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3577
    Prev
    Next
    INDEX
    Explanations

    pants or trousers

    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_39_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
    jacket
    0.50
     jacket
    0.50
    肩
    0.48
     shoulder
    0.48
     Neck
    0.48
    背
    0.48
    肩膀
    0.47
    Neck
    0.46
     Shoulder
    0.45
    Shirt
    0.44
    POSITIVE LOGITS
     trousers
    0.77
     pantalones
    0.76
     pants
    0.73
    👖
    0.66
     pantal
    0.66
    裤
    0.65
    褲
    0.65
     trouser
    0.64
     Pants
    0.61
    pants
    0.60
    Activations Density 0.104%

    No Known Activations