© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59993
    Prev
    Next
    INDEX
    Explanations

    describing code actions and outputs

    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
     ឬ
    0.57
     Чтобы
    0.52
     명이
    0.50
     Архиви
    0.49
    Commande
    0.48
    Chemistry
    0.46
     書き
    0.45
    သုံးပြု
    0.45
     डब्ल्यू
    0.45
     รวม
    0.45
    POSITIVE LOGITS
    ing
    0.59
     indipendente
    0.50
    ם
    0.50
     tranquila
    0.49
    nio
    0.46
     serene
    0.46
     santo
    0.46
     mollus
    0.46
     silenz
    0.46
    c
    0.46
    Activations Density 0.220%

    No Known Activations