© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 30248
    Prev
    Next
    INDEX
    Explanations

    example text

    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_10_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
     rápido
    0.73
     हैव
    0.72
    न्या
    0.72
    ↵↵
    0.70
     पड़े
    0.69
    Referències
    0.68
     มี
    0.67
    se
    0.66
    ter
    0.66
     pesa
    0.65
    POSITIVE LOGITS
    0
    1.22
    <0x80>
    1.11
    ０
    1.09
     ejac
    0.88
    ى
    0.82
    rf
    0.80
     ০১
    0.78
    سرائيل
    0.77
    ره
    0.77
    nata
    0.75
    Activations Density 0.001%

    No Known Activations