© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246184
    Prev
    Next
    INDEX
    Explanations

    political behavior and participation

    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
     політи
    0.37
    评审
    0.37
     паліты
    0.37
     representando
    0.36
    Gpio
    0.35
    чном
    0.35
     경영
    0.35
    写
    0.34
    uren
    0.34
     полити
    0.34
    POSITIVE LOGITS
     quantities
    0.39
     dame
    0.38
     Liv
    0.37
    ResourceManager
    0.37
     success
    0.36
     टिकट
    0.36
     kaynağından
    0.35
     thermal
    0.34
     Erfolg
    0.34
     Success
    0.34
    Activations Density 0.003%

    No Known Activations