© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6780
    Prev
    Next
    INDEX
    Explanations

    I've included

    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_40_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
    之
    0.41
     مساعد
    0.38
    াহিয়া
    0.36
     yaşanan
    0.36
     Cato
    0.35
     papeles
    0.35
    𒊬
    0.34
    ساعد
    0.34
    ทาง
    0.33
     narratives
    0.33
    POSITIVE LOGITS
     avoiding
    0.41
     researched
    0.41
    ローブ
    0.39
    뭇
    0.39
    Avoiding
    0.38
     estimated
    0.38
     प्रोसेसर
    0.38
    estimation
    0.37
     includ
    0.37
    invention
    0.37
    Activations Density 0.163%

    No Known Activations