© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 89051
    Prev
    Next
    INDEX
    Explanations

    National Guard, National University, National Library

    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_11_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
    lassen
    0.54
    лист
    0.54
     الاتحاد
    0.52
    y
    0.50
     Chocolate
    0.50
     এগিয়ে
    0.50
    Experiment
    0.49
    स्टैंड
    0.49
    europe
    0.49
     inverso
    0.48
    POSITIVE LOGITS
     be
    0.64
    يه
    0.63
    ین
    0.57
     dispoz
    0.55
    が悪
    0.54
     entered
    0.54
    បំ
    0.54
    ش
    0.54
     theyre
    0.53
    に行
    0.52
    Activations Density 0.002%

    No Known Activations