© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 19643
    Prev
    Next
    INDEX
    Explanations

    VCS or version control

    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_15_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
    ген
    0.55
    без
    0.52
    昭和
    0.51
    3
    0.47
     COMPO
    0.47
    7
    0.46
    cord
    0.45
    Acc
    0.44
    c
    0.44
     लेकर
    0.44
    POSITIVE LOGITS
    存储
    0.50
     retrieves
    0.49
     caches
    0.48
    HasStarred
    0.48
     শৃঙ্খলা
    0.48
     condiments
    0.47
     gmin
    0.47
    检索
    0.47
    大量的
    0.46
     ambassadors
    0.46
    Activations Density 0.000%

    No Known Activations