© 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. 162629
    Prev
    Next
    INDEX
    Explanations

    World Cup winners

    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
    heta
    0.43
    bett
    0.40
    邊
    0.38
    ভা
    0.38
     Nesta
    0.37
    杣
    0.37
     नाटक
    0.36
     ~(
    0.35
    ഭം
    0.35
    弦
    0.35
    POSITIVE LOGITS
     winner
    0.62
     winners
    0.61
     победи
    0.61
    winners
    0.57
     Winners
    0.56
    Winner
    0.55
     Winner
    0.55
    Winners
    0.55
    winner
    0.54
     venced
    0.52
    Activations Density 0.005%

    No Known Activations