© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 92011
    Prev
    Next
    INDEX
    Explanations

    bike, bear, gravel

    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_3_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
    ot
    0.83
    et
    0.79
    (
    0.76
    ens
    0.71
    ent
    0.68
    od
    0.68
    os
    0.67
    ocent
    0.66
    ings
    0.65
    ou
    0.64
    POSITIVE LOGITS
    。
    0.75
     as
    0.72
    ك
    0.63
     süd
    0.62
     maxim
    0.61
     тысячи
    0.61
     Sebasti
    0.60
     can
    0.60
     styl
    0.60
    、
    0.60
    Activations Density 0.001%

    No Known Activations