© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 65945
    Prev
    Next
    INDEX
    Explanations

    Doctors Without Borders, human rights

    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_41_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
    ﮨ
    0.39
    ಳಿತ
    0.38
    дию
    0.37
    いろ
    0.37
    Overflow
    0.36
    EUR
    0.36
     nField
    0.36
    鞅
    0.36
     سادہ
    0.35
    Isolated
    0.35
    POSITIVE LOGITS
     Human
    0.99
     ह्यूमन
    0.89
    Human
    0.85
     Doctors
    0.82
     Amnesty
    0.78
     HUMAN
    0.78
     HR
    0.77
     Mé
    0.70
    Mé
    0.68
     human
    0.66
    Activations Density 0.001%

    No Known Activations