© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 33491
    Prev
    Next
    INDEX
    Explanations

    clothing and accessories

    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_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Minkowski
    0.28
    ndi
    0.27
    ndez
    0.26
    ELLOW
    0.25
     repas
    0.25
    twin
    0.25
    ʬ
    0.24
    ण्डी
    0.24
    ㄉ
    0.24
    ppsala
    0.24
    POSITIVE LOGITS
     centrifuge
    0.25
     ബാറ്റ
    0.24
     stitch
    0.24
    縫
    0.24
    𝓗
    0.24
     clutter
    0.24
    赫
    0.24
     sewn
    0.23
     εμφ
    0.23
    裱
    0.23
    Activations Density 0.020%

    No Known Activations