© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52375
    Prev
    Next
    INDEX
    Explanations

    prohibitory laws and regulations

    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_31_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
     Unions
    0.41
    棗
    0.39
     Fraud
    0.37
     mantener
    0.35
     szem
    0.35
     cytoplasmic
    0.35
     αδ
    0.35
     اکتوبر
    0.35
     unions
    0.34
    语
    0.34
    POSITIVE LOGITS
     запре
    0.53
    禁止
    0.51
     ban
    0.50
     banning
    0.48
     prohib
    0.48
     emissions
    0.47
     bans
    0.47
     prohibit
    0.46
     banned
    0.44
     prohibiting
    0.43
    Activations Density 0.046%

    No Known Activations