© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 46237
    Prev
    Next
    INDEX
    Explanations

    Pacific Partnership

    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_10_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
    positivo
    0.68
     kiedy
    0.60
    Tổng
    0.57
     daisies
    0.56
     coordinadora
    0.55
    는
    0.54
    ۔
    0.52
     करेंगी
    0.51
     piensan
    0.51
     düşün
    0.50
    POSITIVE LOGITS
    v
    0.61
    ungs
    0.57
    ’
    0.56
    ological
    0.53
    on
    0.50
     rout
    0.50
    ”
    0.49
    ong
    0.49
    www
    0.48
     rm
    0.47
    Activations Density 0.000%

    No Known Activations