© 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. 31175
    Prev
    Next
    INDEX
    Explanations

    Persian Mughal Indian cultural elements

    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
    𝕜
    0.45
     Está
    0.43
     Ritual
    0.40
     ধর্মের
    0.40
     কমিশনের
    0.40
     रथ
    0.40
     resetting
    0.39
    ┝
    0.39
    allenges
    0.38
     Hebrews
    0.38
    POSITIVE LOGITS
     Mughal
    0.55
    Saf
    0.52
     Saf
    0.52
     मुगल
    0.47
     miniatur
    0.45
    wale
    0.45
     Suf
    0.45
     Persian
    0.43
     miniatures
    0.43
     miniature
    0.42
    Activations Density 0.048%

    No Known Activations