© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 238592
    Prev
    Next
    INDEX
    Explanations

    propaganda and influence

    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_32_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
     corridors
    0.42
     scopes
    0.42
    廊
    0.38
     risks
    0.37
     spells
    0.37
    ルド
    0.37
     vascular
    0.37
    razil
    0.37
     hallways
    0.37
     hallway
    0.36
    POSITIVE LOGITS
     propagand
    0.59
     Propaganda
    0.58
     propaganda
    0.57
     propag
    0.41
    宣传
    0.38
     FOREIGN
    0.38
    propag
    0.38
    遑
    0.37
     выпуска
    0.37
     ideological
    0.37
    Activations Density 0.004%

    No Known Activations