© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 207803
    Prev
    Next
    INDEX
    Explanations

    six

    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_46_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
     eight
    0.89
     Eight
    0.89
    八
    0.83
    Eight
    0.80
     oito
    0.76
     八
    0.75
     acht
    0.74
    eight
    0.74
     huit
    0.70
     आठ
    0.70
    POSITIVE LOGITS
     Six
    0.62
    Six
    0.61
    Ten
    0.57
    six
    0.56
     six
    0.55
     Ten
    0.54
    六
    0.50
     छह
    0.50
     सिक्स
    0.49
    Sixth
    0.49
    Activations Density 0.043%

    No Known Activations