© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 40684
    Prev
    Next
    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    Dev
    0.41
     Dev
    0.39
     Teach
    0.39
     ডেলি
    0.39
    ádza
    0.38
     Adventures
    0.38
     ലഭ
    0.38
     Speedy
    0.38
     dev
    0.38
    禇
    0.37
    POSITIVE LOGITS
     era
    0.44
     eram
    0.40
    fter
    0.39
     lot
    0.38
     les
    0.38
     voulez
    0.37
    мере
    0.37
    ః
    0.37
     tongue
    0.36
     holding
    0.36
    Activations Density 0.002%

    No Known Activations