© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171440
    Prev
    Next
    INDEX
    Explanations

    Disneyland or Disney World

    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_20_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
    زيز
    0.49
     ম
    0.48
    byn
    0.47
    zb
    0.43
    zio
    0.43
    empuan
    0.43
    zinho
    0.42
     passi
    0.41
    ית
    0.41
    globalMap
    0.41
    POSITIVE LOGITS
    灲
    0.50
     Raffle
    0.46
    ෘ
    0.44
     gavel
    0.44
     tématu
    0.43
     andra
    0.42
     dél
    0.42
    盾
    0.41
    聪
    0.41
     നിയമ
    0.41
    Activations Density 0.000%

    No Known Activations