© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 32558
    Prev
    Next
    INDEX
    Explanations

    multilingual text

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    收
    1.05
    収
    1.00
     收
    0.93
    收到
    0.85
    收入
    0.84
     thu
    0.84
    收取
    0.80
     recycling
    0.73
     recycle
    0.72
    receive
    0.71
    POSITIVE LOGITS
     Picking
    0.40
    দ্দিন
    0.38
    싱
    0.38
     побу
    0.37
     Figaro
    0.37
     තම
    0.37
    daftar
    0.36
     picking
    0.36
    tyn
    0.36
     Pickering
    0.35
    Activations Density 0.008%

    No Known Activations