© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 230480
    Prev
    Next
    INDEX
    Explanations

    Pokémon GO and Sushi Go!

    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_6_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
    in
    1.30
    지
    1.25
    as
    1.08
    ด
    1.07
    n
    1.00
    the
    0.99
     zespół
    0.97
    ಗೆ
    0.96
     clothe
    0.93
     rapide
    0.92
    POSITIVE LOGITS
    ാരി
    1.05
    <
    0.97
     لأ
    0.92
    Е
    0.88
    мога
    0.87
    もら
    0.86
    Ак
    0.84
     befinden
    0.83
    のです
    0.83
    kev
    0.83
    Activations Density 0.000%

    No Known Activations