© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45832
    Prev
    Next
    INDEX
    Explanations

    domestic roles and housework

    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_13_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    4
    0.56
    â
    0.55
    \",
    0.55
    å
    0.54
    ↵
    0.53
     s
    0.52
    ä
    0.50
    rev
    0.50
    quick
    0.50
    \"
    0.49
    POSITIVE LOGITS
     limpia
    0.69
     maids
    0.66
     cleaners
    0.64
     atraer
    0.63
     limpiar
    0.62
    ଚ
    0.62
     humild
    0.61
     tangan
    0.61
     limpio
    0.61
    राधना
    0.60
    Activations Density 0.002%

    No Known Activations