© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 47218
    Prev
    Next
    INDEX
    Explanations

    chess champions and championships

    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_13_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
     herv
    0.55
     Emer
    0.55
    </h3>
    0.54
     Phil
    0.54
    f
    0.54
     tornou
    0.53
    c
    0.53
     provenienti
    0.52
     Employer
    0.51
     pitt
    0.50
    POSITIVE LOGITS
    इसके
    0.47
    $$\
    0.47
    '
    0.47
    Some
    0.47
    Um
    0.46
    鬢
    0.46
    US
    0.45
     หน่อย
    0.45
    VIOUS
    0.45
    一些
    0.45
    Activations Density 0.001%

    No Known Activations