© 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. 90316
    Prev
    Next
    INDEX
    Explanations

    written resources, code, audio, and trained models

    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
     kona
    0.40
     hemic
    0.40
     希望
    0.40
    endif
    0.40
     rind
    0.39
     cunt
    0.39
    禕
    0.39
     стратегия
    0.38
    鈞
    0.38
     наде
    0.38
    POSITIVE LOGITS
    的时候
    0.39
     plotter
    0.38
     Bott
    0.38
    artists
    0.37
    variety
    0.36
    werben
    0.36
    bey
    0.36
    bott
    0.36
     Processes
    0.35
    setPointSize
    0.35
    Activations Density 0.044%

    No Known Activations