© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 65047
    Prev
    Next
    INDEX
    Explanations

    Sanctions, Francisco, Sanitization

    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_41_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
     san
    0.64
    サン
    0.62
     산
    0.61
    San
    0.58
     San
    0.57
    san
    0.57
     sanctions
    0.56
     sanctioned
    0.56
     SAN
    0.54
     Sn
    0.53
    POSITIVE LOGITS
     vaisse
    0.40
    ចេញ
    0.38
    гү
    0.38
    ='',
    0.38
    émor
    0.38
    曲
    0.38
    厷
    0.37
    čí
    0.37
     pathogenesis
    0.37
    éma
    0.36
    Activations Density 0.001%

    No Known Activations