© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 161446
    Prev
    Next
    INDEX
    Explanations

    so, also, and so on

    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_31_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
    ุท
    0.43
    ome
    0.37
    امه
    0.36
     dome
    0.36
    лень
    0.34
     Franchise
    0.33
     aber
    0.33
     franch
    0.33
    افه
    0.33
    ➷
    0.33
    POSITIVE LOGITS
    Bez
    0.37
    bez
    0.34
    㳑
    0.34
    朧
    0.33
    orsun
    0.32
     diferenciar
    0.32
    beza
    0.32
     које
    0.31
    स्वर
    0.30
    equations
    0.30
    Activations Density 0.000%

    No Known Activations