© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212003
    Prev
    Next
    INDEX
    Explanations

    spokesperson

    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_5_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
    t
    1.42
    ﺔ
    1.27
    in
    1.26
    ‌ای
    1.16
    ه‌های
    1.13
    ‌ترین
    1.13
    를
    1.12
    ‌های
    1.11
    ه‌ای
    1.09
    .’
    1.08
    POSITIVE LOGITS
    ling
    1.09
    1.04
    点
    1.01
    ла
    0.96
    ↵↵
    0.96
    ymmetry
    0.90
    lov
    0.88
    ?
    0.87
     It
    0.86
    éli
    0.84
    Activations Density 0.000%

    No Known Activations