© 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. 177326
    Prev
    Next
    INDEX
    Explanations

    fast response, setup, shipping

    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
     bustling
    0.35
    槅
    0.34
     beatae
    0.34
     bahwa
    0.33
     accion
    0.33
     indifer
    0.32
     Please
    0.32
     berfungsi
    0.32
     berbentuk
    0.32
    踉
    0.32
    POSITIVE LOGITS
    Japan
    0.42
    日本の
    0.38
    Tokyo
    0.37
    High
    0.37
    Es
    0.37
    Water
    0.35
    Sy
    0.34
     Kein
    0.34
    Hö
    0.34
    Windows
    0.34
    Activations Density 0.001%

    No Known Activations