© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 200096
    Prev
    Next
    INDEX
    Explanations

    treaty established

    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_9_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
     INCLUDE
    0.54
     alcanz
    0.53
    깁
    0.51
    К
    0.50
     distributes
    0.48
     doesnt
    0.46
     Tätigkeit
    0.46
    NEEDED
    0.46
    PLACES
    0.46
     działalności
    0.46
    POSITIVE LOGITS
    分辨
    0.57
    om
    0.52
    ani
    0.51
    ema
    0.50
    ano
    0.49
    immer
    0.49
    g
    0.49
    man
    0.49
    amb
    0.48
    vis
    0.48
    Activations Density 0.000%

    No Known Activations