© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57522
    Prev
    Next
    INDEX
    Explanations

    voodoo dolls and cult leaders

    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_11_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
    များကို
    0.57
     Darrell
    0.54
     cumprimento
    0.54
     سارے
    0.50
     renter
    0.49
    掇
    0.49
     দিচ্ছেন
    0.49
     reconciling
    0.49
     dioxide
    0.48
     obeying
    0.48
    POSITIVE LOGITS
    。”
    0.57
    不
    0.52
    フ
    0.51
    ガン
    0.50
    Lith
    0.50
    )”
    0.48
     کھ
    0.47
    菊
    0.47
    Bild
    0.47
    レ
    0.47
    Activations Density 0.020%

    No Known Activations