© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 207641
    Prev
    Next
    INDEX
    Explanations

    detergent

    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_46_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
     Lean
    0.39
    狹
    0.38
    傷
    0.38
    ளு
    0.37
    PageComponent
    0.36
    ︿
    0.36
    ირო
    0.36
    нуть
    0.36
    李
    0.36
    仙
    0.36
    POSITIVE LOGITS
     deter
    0.96
     cleansing
    0.91
     deterg
    0.90
     detergent
    0.87
     detergents
    0.83
    deter
    0.83
     Deter
    0.82
     cleanser
    0.81
     foaming
    0.80
     emuls
    0.77
    Activations Density 0.016%

    No Known Activations