© 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. 30472
    Prev
    Next
    INDEX
    Explanations

    name, followed by a comma

    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
     ஆம்
    0.44
     стр
    0.43
    निम
    0.41
     Gave
    0.39
     Havre
    0.38
     Outlet
    0.38
    ᖁ
    0.37
     dejó
    0.37
    Letters
    0.37
    ⅲ
    0.36
    POSITIVE LOGITS
     PRODUCTION
    0.41
     hardware
    0.41
    Hardware
    0.40
     Hardware
    0.40
    HW
    0.39
     HW
    0.39
     чувстви
    0.39
    hardware
    0.38
    িত্ত
    0.37
    PRODUCTION
    0.36
    Activations Density 0.000%

    No Known Activations