© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 57556
    Prev
    Next
    INDEX
    Explanations

    discord

    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_59_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
     Robots
    0.50
     О
    0.48
     .$
    0.45
     $,
    0.42
    Robot
    0.42
     М
    0.42
     $.
    0.41
     O
    0.40
    𝐘
    0.40
    My
    0.40
    POSITIVE LOGITS
    app
    0.44
    iaz
    0.43
    奋斗
    0.40
    ứng
    0.38
     parete
    0.38
    iazioni
    0.38
     universitario
    0.38
     xi
    0.37
    ovil
    0.37
    iej
    0.37
    Activations Density 0.000%

    No Known Activations