© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 140568
    Prev
    Next
    INDEX
    Explanations

    special characters

    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_46_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
    ั่ง
    0.39
     ensu
    0.39
     betas
    0.38
    Minimized
    0.38
     میکس
    0.38
     बाध्य
    0.37
    쬐
    0.37
     stalls
    0.37
     discrete
    0.37
     telephone
    0.36
    POSITIVE LOGITS
    섹
    0.44
    луйста
    0.40
    bullets
    0.39
     pérd
    0.37
     बुल
    0.37
    提起
    0.37
    ERTY
    0.37
    sprecher
    0.37
     প্রত্যেকের
    0.36
    Quarter
    0.36
    Activations Density 0.001%

    No Known Activations