© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 208983
    Prev
    Next
    INDEX
    Explanations

    light and shine

    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_56_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
     flick
    0.70
     бли
    0.69
     shine
    0.68
     overflow
    0.61
     overflows
    0.61
    辉
    0.60
     glare
    0.58
    輝
    0.57
     Overflow
    0.56
    shine
    0.55
    POSITIVE LOGITS
    خش
    0.91
    خ
    0.68
    ﺨ
    0.40
     玉
    0.38
     در
    0.38
     "-//
    0.37
    хом
    0.37
    usses
    0.36
    winfx
    0.36
    ogun
    0.36
    Activations Density 0.006%

    No Known Activations