© 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. 163528
    Prev
    Next
    INDEX
    Explanations

    state-sponsored persecution, statecraft, state ideology

    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
    ۊ
    0.42
    IOUS
    0.38
    зумі
    0.38
    发现
    0.38
     Javier
    0.38
    就算
    0.37
    AspNetUser
    0.37
    いません
    0.37
    ırmızı
    0.36
    宇
    0.36
    POSITIVE LOGITS
     состояние
    0.43
     Less
    0.41
     रखे
    0.39
     Sect
    0.39
     state
    0.37
    sec
    0.36
     sto
    0.36
     состоянии
    0.35
    界
    0.35
     상태
    0.35
    Activations Density 0.000%

    No Known Activations