© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 232232
    Prev
    Next
    INDEX
    Explanations

    variable assignment with `=`

    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_32_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
    \(
    0.37
     Webber
    0.35
     sende
    0.35
     пять
    0.34
    \[
    0.34
    แจ
    0.34
    mom
    0.34
    athl
    0.34
     сти
    0.33
     кукуру
    0.33
    POSITIVE LOGITS
    ArchiveAction
    0.48
     मनोवैज्ञानिक
    0.41
    కుంది
    0.38
     développé
    0.37
    圻
    0.37
     Suitable
    0.36
     compiles
    0.36
     IPA
    0.36
    hwar
    0.35
     lutego
    0.35
    Activations Density 0.002%

    No Known Activations