© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 219809
    Prev
    Next
    INDEX
    Explanations

    black churches, Juneteenth, freedmen

    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
    Not in Any Lists

    No Comments

    Negative Logits
    查
    0.37
     verfol
    0.36
    bash
    0.36
    Auf
    0.35
    ivist
    0.34
     تنفيذ
    0.34
     bau
    0.33
     Auf
    0.33
    словия
    0.33
     executive
    0.32
    POSITIVE LOGITS
    竅
    0.41
    preserved
    0.40
    掙
    0.39
    ಟ್‌
    0.38
     umjet
    0.38
    ையம்
    0.38
     grd
    0.38
    excluded
    0.37
    heritage
    0.37
     patrimonio
    0.37
    Activations Density 0.000%

    No Known Activations