© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10576
    Prev
    Next
    INDEX
    Explanations

    Chinese Communist Party leaders

    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
     contour
    0.40
     corporation
    0.38
    DebugTest
    0.38
     contours
    0.36
    stery
    0.36
     المسا
    0.36
    rée
    0.35
    镖
    0.35
     leakage
    0.35
     hops
    0.35
    POSITIVE LOGITS
     Polit
    1.43
     polit
    1.23
    Polit
    1.19
     Central
    1.09
    Central
    1.02
     CENTRAL
    0.91
     POLIT
    0.91
    polit
    0.89
    中央
    0.80
     поли
    0.77
    Activations Density 0.013%

    No Known Activations