© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 237391
    Prev
    Next
    INDEX
    Explanations

    human rights

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    颳
    0.38
    overleftarrow
    0.37
    awati
    0.35
     IIS
    0.35
    iis
    0.34
    ヌ
    0.34
    搞笑
    0.34
    بە
    0.34
    銛
    0.33
    茍
    0.33
    POSITIVE LOGITS
     human
    2.97
     Human
    2.83
    Human
    2.77
    human
    2.63
     HUMAN
    2.42
     челове
    2.38
     ह्यूमन
    2.11
     인간
    2.09
     чове
    2.02
    人間の
    1.98
    Activations Density 0.002%

    No Known Activations