© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 77273
    Prev
    Next
    INDEX
    Explanations

    glfw window hints

    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_29_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
    \&
    0.38
     FCC
    0.37
     Osm
    0.37
     Advis
    0.37
     徐
    0.36
     Lyric
    0.36
     Arbitration
    0.35
     GM
    0.35
     Rebecca
    0.34
     duckys
    0.34
    POSITIVE LOGITS
     frapp
    0.42
     steppe
    0.40
     láp
    0.39
     των
    0.38
     longues
    0.36
    ➛
    0.36
     canyon
    0.36
    ῆ
    0.35
     sustit
    0.34
    াবাহ
    0.34
    Activations Density 0.000%

    No Known Activations