© 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. 200055
    Prev
    Next
    INDEX
    Explanations

    code formatting style

    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
     whereupon
    0.41
     Gottes
    0.38
    zeichen
    0.37
     kült
    0.37
     nought
    0.37
    0.37
     Kass
    0.36
     voire
    0.36
    igure
    0.35
    styl
    0.35
    POSITIVE LOGITS
     回
    0.41
    Uniform
    0.38
     alg
    0.38
     আত্মসম
    0.38
     Camar
    0.38
     प्र
    0.37
    urndata
    0.37
     código
    0.36
     camar
    0.36
    మా
    0.36
    Activations Density 0.001%

    No Known Activations