© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 26724
    Prev
    Next
    INDEX
    Explanations

    .ini configuration files

    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_40_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
    肐
    0.44
     vuelta
    0.43
    лын
    0.40
     duckys
    0.40
     chast
    0.39
     viewer
    0.39
    酎
    0.39
    षी
    0.38
    wahati
    0.38
    vvvert
    0.37
    POSITIVE LOGITS
    Interpol
    0.78
     Interpol
    0.71
     interpolation
    0.69
     interpol
    0.64
    interpolation
    0.62
     interpolated
    0.61
    interpol
    0.59
     interpolate
    0.55
    interpolate
    0.54
    的使用
    0.45
    Activations Density 0.001%

    No Known Activations