© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 200227
    Prev
    Next
    INDEX
    Explanations

    or

    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_37_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
    ijoje
    0.40
    uhnya
    0.40
    めで
    0.38
     বহুম
    0.38
    ല്ലാത്ത
    0.37
     বিখ্যাত
    0.37
     Bold
    0.36
    famous
    0.36
     எல்லோ
    0.35
    </body>
    0.35
    POSITIVE LOGITS
     หรือ
    0.80
     hoặc
    0.79
    或是
    0.77
     或
    0.75
     किंवा
    0.75
     atau
    0.73
     veya
    0.73
    或
    0.73
     или
    0.72
     অথবা
    0.72
    Activations Density 0.002%

    No Known Activations