© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11937
    Prev
    Next
    INDEX
    Explanations

    performance tuning

    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_13_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
    ADY
    0.57
    pción
    0.57
    quisition
    0.53
    (
    0.52
     مجموعة
    0.51
    zado
    0.50
    ude
    0.49
     تقدم
    0.48
    rones
    0.48
    ğini
    0.48
    POSITIVE LOGITS
    する
    0.54
    ла
    0.52
    ри
    0.51
     фаразлау
    0.51
     vời
    0.50
     मतदार
    0.49
    け
    0.49
    ве
    0.48
     វា
    0.48
     bolstering
    0.48
    Activations Density 0.004%

    No Known Activations