© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 205306
    Prev
    Next
    INDEX
    Explanations

    framed as

    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_10_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
    с
    0.95
    ot
    0.93
     frame
    0.89
    are
    0.88
    ла
    0.83
    og
    0.80
    ți
    0.79
    frame
    0.79
     Frame
    0.77
     can
    0.75
    POSITIVE LOGITS
    ABLES
    0.73
    婍
    0.71
    䆔
    0.70
    人們
    0.69
     extremes
    0.68
    梫
    0.68
     orchards
    0.66
     opposites
    0.64
    𝐼
    0.64
     gradients
    0.64
    Activations Density 0.004%

    No Known Activations