© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 215924
    Prev
    Next
    INDEX
    Explanations

    bc followed by x or 4

    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_5_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
    >∕
    1.19
    IAN
    1.05
    IZE
    1.05
    end
    1.02
    ۳
    1.02
    inį
    1.01
    an
    0.97
    ates
    0.93
    IOR
    0.93
    IEN
    0.91
    POSITIVE LOGITS
    ,
    1.48
    ة
    1.45
     that
    1.39
    та
    1.18
    ↵↵
    1.17
    ט
    1.15
    ת
    1.11
    л
    1.09
    ני
    1.07
    ूण
    1.06
    Activations Density 0.000%

    No Known Activations