© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 15090
    Prev
    Next
    INDEX
    Explanations

    galaxy and Andromeda

    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_13_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
     ಕೊಡ
    0.53
    os
    0.51
     घात
    0.51
     ձ
    0.50
    derick
    0.49
     hỗ
    0.49
     പങ്ക
    0.49
    achievement
    0.48
     ।
    0.48
     Bá
    0.48
    POSITIVE LOGITS
     galaxy
    0.61
     galactic
    0.56
     circular
    0.54
     supernovae
    0.54
     extruder
    0.53
     we
    0.53
     extrav
    0.53
     Andromeda
    0.52
     stellar
    0.51
     galaxies
    0.51
    Activations Density 0.020%

    No Known Activations