© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 46490
    Prev
    Next
    INDEX
    Explanations

    like a human

    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_22_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
     рады
    0.26
     tabular
    0.25
     gran
    0.24
    낮
    0.23
    ieran
    0.23
     graf
    0.22
     тон
    0.22
     osk
    0.22
     grand
    0.21
     bronce
    0.21
    POSITIVE LOGITS
    Aqui
    0.26
    爆
    0.25
     aircraft
    0.24
     допомогою
    0.23
    Aircraft
    0.23
    troops
    0.23
     Trotsky
    0.23
    trop
    0.23
    Trop
    0.23
    ativity
    0.22
    Activations Density 0.016%

    No Known Activations