© 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. 37076
    Prev
    Next
    INDEX
    Explanations

    say "planet"

    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
     polymorphisms
    0.40
     ماشي
    0.38
     خون
    0.36
     Quis
    0.36
     ขวด
    0.35
     Gertrude
    0.34
     cổng
    0.34
    쫑
    0.33
     bottle
    0.33
    jose
    0.33
    POSITIVE LOGITS
    Planet
    2.97
     Planet
    2.95
     planet
    2.94
     плане
    2.84
    planet
    2.73
     Plan
    2.63
    Plan
    2.56
     planeta
    2.53
     PLAN
    2.52
     planète
    2.34
    Activations Density 0.033%

    No Known Activations