© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 89298
    Prev
    Next
    INDEX
    Explanations

    husband

    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_60_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
     and
    0.49
    udo
    0.47
    uć
    0.45
     Архив
    0.44
    osi
    0.44
    enter
    0.43
    .</
    0.43
    ey
    0.43
    i
    0.43
    malı
    0.42
    POSITIVE LOGITS
     husband
    0.80
     Husband
    0.72
    夫
    0.70
     suami
    0.67
    らを
    0.63
    husband
    0.62
    ら
    0.60
     husbands
    0.58
     marito
    0.58
     hubby
    0.58
    Activations Density 0.000%

    No Known Activations