© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 804
    Prev
    Next
    INDEX
    Explanations

    HTML head section

    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
    တို့ကို
    0.43
    angerschaft
    0.42
    getHeader
    0.41
     रिक्वायरमेंट
    0.40
    푦
    0.40
     चुनावों
    0.39
     Lapse
    0.39
     transcripts
    0.38
    izei
    0.38
     marqué
    0.38
    POSITIVE LOGITS
    核心
    0.39
    XmlElement
    0.39
    天气
    0.38
    슬
    0.38
    XML
    0.38
     üst
    0.38
    Ки
    0.37
     unbelievable
    0.37
    content
    0.36
    ᆨ
    0.36
    Activations Density 0.001%

    No Known Activations