© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199297
    Prev
    Next
    INDEX
    Explanations

    table tennis, drum pads, nine moveable cards

    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_12_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
     методы
    0.54
     pati
    0.53
     ३
    0.52
     idha
    0.52
     basilica
    0.52
     puriso
    0.52
     ต
    0.51
     ۳
    0.51
     metodi
    0.50
     synchrotron
    0.50
    POSITIVE LOGITS
    luss
    0.57
    M
    0.54
    ings
    0.53
    igen
    0.53
    icides
    0.53
    ann
    0.52
    sächlich
    0.52
    back
    0.52
    holder
    0.52
    ベーション
    0.51
    Activations Density 0.000%

    No Known Activations