© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 19034
    Prev
    Next
    INDEX
    Explanations

    python self and df

    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_34_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
     desir
    0.40
    ংস
    0.39
     Д
    0.37
    elands
    0.36
     gracious
    0.36
     bong
    0.35
     therefore
    0.35
     daring
    0.34
    ኙ
    0.34
     herb
    0.34
    POSITIVE LOGITS
    Tah
    0.45
    镐
    0.40
    schluss
    0.39
    Nana
    0.38
    गाय
    0.37
     svoju
    0.37
     swój
    0.36
    স্কার
    0.36
    GAM
    0.36
    $^
    0.36
    Activations Density 0.102%

    No Known Activations