© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 176854
    Prev
    Next
    INDEX
    Explanations

    list of dictionaries

    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_20_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
    /
    0.46
     Liber
    0.43
    iled
    0.40
    imente
    0.39
    iloc
    0.38
    gi
    0.38
    ilo
    0.38
    弦
    0.38
    zieh
    0.37
    ob
    0.37
    POSITIVE LOGITS
    Through
    0.51
     melalui
    0.50
    :_
    0.50
     attraverso
    0.50
    Does
    0.48
     Through
    0.47
     :{
    0.46
     Aws
    0.45
     WHICH
    0.45
     через
    0.44
    Activations Density 0.004%

    No Known Activations