© 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. 137333
    Prev
    Next
    INDEX
    Explanations

    LG, Strand, Lea, Catering, Food, Mang

    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
    6
    0.57
    ueling
    0.54
    ua
    0.50
    isent
    0.48
    licks
    0.45
    wic
    0.45
    ys
    0.45
    は
    0.45
     Potter
    0.44
    attr
    0.43
    POSITIVE LOGITS
    ሌ
    0.47
     astrophysics
    0.46
     pelaksanaan
    0.46
     инструкции
    0.46
     итальян
    0.45
     изучение
    0.44
     наших
    0.44
    因为
    0.44
     beetroot
    0.43
    娉
    0.43
    Activations Density 0.001%

    No Known Activations