© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 88216
    Prev
    Next
    INDEX
    Explanations

    at the time of

    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_18_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
     کارکن
    0.50
     замены
    0.49
    З
    0.48
     रद्द
    0.48
    Вы
    0.47
    any
    0.46
    ton
    0.45
     mascot
    0.45
     직원
    0.45
    isa
    0.44
    POSITIVE LOGITS
    PTMR
    0.50
    の問題
    0.44
     Rate
    0.43
    চিত্রে
    0.43
     VGM
    0.43
    公平
    0.43
    ⅴ
    0.43
    elect
    0.43
     JOptionPane
    0.43
    ঙ্কের
    0.43
    Activations Density 0.001%

    No Known Activations