© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 76838
    Prev
    Next
    INDEX
    Explanations

    elimination or final

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
     باش
    0.41
     résolution
    0.39
    љи
    0.39
    azoo
    0.38
     تاس
    0.38
    ongo
    0.38
    achy
    0.37
    atitis
    0.37
     renou
    0.37
    ।--
    0.37
    POSITIVE LOGITS
     élim
    0.51
     elimin
    0.50
    選
    0.50
     finale
    0.47
     finales
    0.46
     Finale
    0.45
     Elimin
    0.45
     finais
    0.45
     eliminar
    0.45
    Elim
    0.45
    Activations Density 0.001%

    No Known Activations