© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 180057
    Prev
    Next
    INDEX
    Explanations

    names and places

    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_50_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
    吏
    0.44
     Carm
    0.42
     Inch
    0.42
     Ja
    0.40
     ja
    0.38
     jaun
    0.38
     bust
    0.37
    Inch
    0.37
     inch
    0.36
    Ja
    0.36
    POSITIVE LOGITS
     Vitor
    0.66
     V
    0.62
     Vit
    0.61
    Santos
    0.60
    Vit
    0.58
     Santos
    0.56
     SANT
    0.56
     Vitória
    0.55
     VIT
    0.53
     santos
    0.53
    Activations Density 0.008%

    No Known Activations