© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 174670
    Prev
    Next
    INDEX
    Explanations

    database column definitions

    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_24_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
     specifics
    0.40
     Loaded
    0.40
     loaded
    0.40
     headlined
    0.39
     видно
    0.38
     Squ
    0.37
     poursu
    0.36
     squats
    0.36
    ⃞
    0.36
     namely
    0.36
    POSITIVE LOGITS
    okee
    0.39
    ił
    0.38
    一种
    0.37
    гов
    0.37
    dist
    0.36
    aanse
    0.36
    Dist
    0.35
    ृती
    0.35
    author
    0.35
    ał
    0.35
    Activations Density 0.001%

    No Known Activations