© 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. 51559
    Prev
    Next
    INDEX
    Explanations

    describing an invention

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ள்ளனர்
    0.76
    cara
    0.74
    z
    0.73
    ers
    0.72
     baju
    0.71
     GFP
    0.70
     μια
    0.69
    на
    0.68
     artyku
    0.68
    PhysRev
    0.67
    POSITIVE LOGITS
    IS
    0.80
    न
    0.79
    이었
    0.76
    یم
    0.75
    ुप
    0.74
    ुण
    0.73
    ن
    0.73
    ীয়
    0.69
    ন
    0.68
    的多
    0.66
    Activations Density 0.002%

    No Known Activations