© 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. 28962
    Prev
    Next
    INDEX
    Explanations

    **restrictions on freedoms or control**

    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
    បី
    0.37
    제곱
    0.36
    珊
    0.36
     unprotected
    0.36
     rebellion
    0.35
    Optional
    0.35
     overthrow
    0.34
    斗
    0.34
     regime
    0.34
    ไร
    0.34
    POSITIVE LOGITS
     restrict
    0.63
    制限
    0.60
     restriction
    0.59
    Restriction
    0.59
    限制
    0.57
     Restrictions
    0.57
     restrictions
    0.57
    Restrictions
    0.56
    restriction
    0.54
     ограничения
    0.54
    Activations Density 0.012%

    No Known Activations