© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 232178
    Prev
    Next
    INDEX
    Explanations

    means

    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_32_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
    Rav
    0.46
     Kiel
    0.41
    dll
    0.39
     രാ
    0.38
    打印
    0.38
     RAV
    0.38
     BlogPost
    0.38
    Negative
    0.38
     Rav
    0.38
    骐
    0.37
    POSITIVE LOGITS
     inertia
    0.47
    conserv
    0.42
    inertia
    0.42
    ская
    0.39
     damped
    0.39
    momentum
    0.38
     momentum
    0.37
     solids
    0.36
     inertial
    0.36
    **/
    0.35
    Activations Density 0.003%

    No Known Activations