© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 49449
    Prev
    Next
    INDEX
    Explanations

    Constitutional AI

    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_10_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
    ب
    0.45
    ف
    0.38
    ের
    0.37
     чувство
    0.36
    الن
    0.35
    ों
    0.35
    手的
    0.35
    路的
    0.35
    s
    0.35
    𝗣
    0.34
    POSITIVE LOGITS
    7
    0.37
    ley
    0.34
    ki
    0.34
    lenme
    0.33
    3
    0.32
    4
    0.31
     ultra
    0.31
     Jain
    0.31
    น่า
    0.31
    lyn
    0.31
    Activations Density 0.006%

    No Known Activations