© 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. 31627
    Prev
    Next
    INDEX
    Explanations

    illegal activities and transactions

    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
    চ্য
    0.39
     Сере
    0.39
    聸
    0.39
    অপহরণ
    0.38
     oppress
    0.37
     mouvement
    0.36
     opro
    0.36
    晤
    0.36
     ʼ
    0.35
     टै
    0.35
    POSITIVE LOGITS
     crack
    0.60
     Crack
    0.46
     cracking
    0.45
    Crack
    0.43
    crack
    0.43
     cracked
    0.42
     kok
    0.42
     кок
    0.41
     Kok
    0.41
     cracks
    0.39
    Activations Density 0.034%

    No Known Activations