© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 15194
    Prev
    Next
    INDEX
    Explanations

    propaganda and influence campaigns

    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_13_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    तेला
    0.50
    телями
    0.49
    эль
    0.48
    车型
    0.48
    َ
    0.48
    λει
    0.47
    permalink
    0.47
     denna
    0.47
    
    0.46
    ramp
    0.46
    POSITIVE LOGITS
     doce
    0.50
     apl
    0.48
     पीने
    0.46
    ួត
    0.45
    絘
    0.45
    ){\
    0.45
     CuSO
    0.45
     chlorine
    0.45
     TFT
    0.44
     kinetic
    0.44
    Activations Density 0.047%

    No Known Activations