© 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
    2. Gemma-3-27B-IT
    3. 51-GEMMASCOPE-2-TRANSCODER-262K
    4. 68380
    Prev
    Next
    INDEX
    Explanations

    Thai 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_51_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
    Ŭ
    0.45
    mouseenter
    0.40
     Canary
    0.38
     Ackerman
    0.38
     стану
    0.38
    錒
    0.38
    msg
    0.37
     পর্ব
    0.37
    áculos
    0.37
    UCK
    0.37
    POSITIVE LOGITS
    wei
    0.44
    Wei
    0.43
     wei
    0.39
    chromiumfx
    0.38
    েন্দ্রনাথ
    0.38
    داً
    0.38
    chrotron
    0.37
    劉
    0.37
    룡
    0.37
    دا
    0.37
    Activations Density 0.000%

    No Known Activations