© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 221446
    Prev
    Next
    INDEX
    Explanations

    containment of communism and Soviet 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_31_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
     priorité
    0.41
     سافٹ
    0.40
    STEIN
    0.40
    SizeF
    0.39
    Termination
    0.39
     informatics
    0.39
    AspectRatio
    0.38
    memo
    0.37
     aspectRatio
    0.37
    晋
    0.37
    POSITIVE LOGITS
    ility
    0.39
     mast
    0.38
     करोगे
    0.36
     ana
    0.36
     சக
    0.35
    坫
    0.35
     cry
    0.35
     ჭ
    0.35
    hex
    0.34
     Isi
    0.34
    Activations Density 0.003%

    No Known Activations