© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120997
    Prev
    Next
    INDEX
    Explanations

    sexual relationships or forbidden intimacy

    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_27_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
    ್‌
    0.42
    琴
    0.40
     простых
    0.39
    dinner
    0.39
    ranial
    0.38
     বিকাশ
    0.38
    飛
    0.38
     ഉയ
    0.38
    ława
    0.38
    Dinner
    0.38
    POSITIVE LOGITS
     sexually
    0.45
     Sexual
    0.43
     sexual
    0.40
     fratern
    0.40
     lubrication
    0.39
     أخ
    0.39
     Married
    0.38
     Moral
    0.38
     lubric
    0.38
     ','
    0.38
    Activations Density 0.089%

    No Known Activations