© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 154704
    Prev
    Next
    INDEX
    Explanations

    sys, os, string module usage

    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_23_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
     businesses
    0.45
     ميد
    0.43
     persons
    0.41
     kt
    0.38
    矢
    0.37
     Surveys
    0.37
    ρευ
    0.36
     tournée
    0.36
     pov
    0.35
     推
    0.35
    POSITIVE LOGITS
    ácil
    0.41
     fichero
    0.39
    Ха
    0.38
    Haryana
    0.38
     Convolution
    0.38
     Weights
    0.37
    plotlib
    0.37
     કરશે
    0.37
     Cavalry
    0.37
     colourful
    0.37
    Activations Density 0.000%

    No Known Activations