© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10745
    Prev
    Next
    INDEX
    Explanations

    adultery and affairs

    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_40_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
    髖
    0.37
    拡
    0.35
     गोद
    0.34
     tumor
    0.34
    osoma
    0.33
    stof
    0.33
     র‌্যা
    0.33
     biops
    0.33
    ্টো
    0.33
    猕
    0.33
    POSITIVE LOGITS
     adultery
    1.03
     adulter
    0.97
     Ad
    0.75
     ад
    0.73
    Ad
    0.69
     adul
    0.65
     Ад
    0.60
     الاد
    0.55
     ad
    0.53
     Adler
    0.53
    Activations Density 0.018%

    No Known Activations