© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18902
    Prev
    Next
    INDEX
    Explanations

    Afghanistan, Taliban, or Muslim contexts

    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_40_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
    irp
    0.40
    مان
    0.39
     jir
    0.37
     Afghans
    0.37
    有効
    0.36
    amai
    0.36
    賴
    0.36
    잿
    0.36
    ოში
    0.35
     bone
    0.35
    POSITIVE LOGITS
     Matsumoto
    0.40
     обо
    0.40
     इस्लामिक
    0.38
    OptionsMenu
    0.38
     DIA
    0.37
    DIA
    0.37
    Muslim
    0.37
     Ganges
    0.37
     conquered
    0.35
     CRIS
    0.35
    Activations Density 0.000%

    No Known Activations