© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 46275
    Prev
    Next
    INDEX
    Explanations

    tried to

    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
    ل
    0.60
    ي
    0.45
    л
    0.40
    ب
    0.40
     CRL
    0.39
    l
    0.38
    家
    0.38
    디
    0.38
    ル
    0.36
    ล
    0.36
    POSITIVE LOGITS
    شی
    0.42
    asth
    0.42
    ному
    0.40
    ‌ای
    0.39
    reicher
    0.39
    obs
    0.38
    казать
    0.38
    zocht
    0.38
    razole
    0.38
    示した
    0.38
    Activations Density 0.007%

    No Known Activations