© 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. 17434
    Prev
    Next
    INDEX
    Explanations

    communist elections and allegations

    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
    军
    0.68
    Military
    0.61
    軍
    0.61
     Military
    0.57
    Army
    0.57
    military
    0.55
    军队
    0.53
     military
    0.53
    군
    0.53
     army
    0.50
    POSITIVE LOGITS
     Communist
    0.46
     communist
    0.43
     confusion
    0.42
     confus
    0.40
    ერს
    0.39
     communism
    0.39
     confusing
    0.39
     भ्रम
    0.38
    omel
    0.38
     কমিউনিস্ট
    0.37
    Activations Density 0.036%

    No Known Activations