© 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. 248031
    Prev
    Next
    INDEX
    Explanations

    blizzard conditions

    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
     heavy
    0.91
    Heavy
    0.83
     Heavy
    0.82
    heavy
    0.75
     тяже
    0.71
     тяжё
    0.61
     cięż
    0.60
     ağır
    0.60
    重
    0.59
     strong
    0.57
    POSITIVE LOGITS
     band
    0.85
    band
    0.84
     bands
    0.82
    bands
    0.79
     BAND
    0.76
    Band
    0.75
     Band
    0.72
    BAND
    0.71
     Bands
    0.70
     banda
    0.67
    Activations Density 0.002%

    No Known Activations