© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 243002
    Prev
    Next
    INDEX
    Explanations

    hentai, Henkel, restriction

    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
     gesetz
    0.39
     Core
    0.38
     CORE
    0.37
    ங்கிணை
    0.36
     oauth
    0.36
     ^{\
    0.35
    φέρει
    0.35
     NO
    0.34
    werten
    0.34
    ٸ
    0.34
    POSITIVE LOGITS
    Restriction
    0.41
     Restriction
    0.41
    จุ
    0.39
     restriction
    0.38
    限制
    0.37
     माण
    0.37
    Jan
    0.36
    restriction
    0.36
     unip
    0.36
     Quân
    0.36
    Activations Density 0.001%

    No Known Activations