© 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. 83928
    Prev
    Next
    INDEX
    Explanations

    code structure initializer

    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
     FLY
    0.37
     LOST
    0.37
    पेड
    0.36
     Granted
    0.35
     thumbnailUrl
    0.35
     granted
    0.34
     deliveries
    0.34
     Arguments
    0.34
    ക
    0.34
    आव
    0.34
    POSITIVE LOGITS
    Segment
    0.39
    neus
    0.37
    ndim
    0.36
     showError
    0.36
     eruption
    0.36
     sectores
    0.36
     methylene
    0.36
    uant
    0.35
     konci
    0.35
    segment
    0.35
    Activations Density 0.000%

    No Known Activations