© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91630
    Prev
    Next
    INDEX
    Explanations

    critically

    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_11_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
     ಯು
    0.63
    ā
    0.57
    וק
    0.55
    ítmény
    0.55
    ্লা
    0.54
     jarang
    0.54
     জটিল
    0.52
     অসুস্থ
    0.52
     विश्
    0.52
     অস্ব
    0.50
    POSITIVE LOGITS
    G
    0.67
     home
    0.62
    M
    0.61
    est
    0.58
    S
    0.57
    D
    0.57
    B
    0.57
    3
    0.55
    shell
    0.54
     duplex
    0.54
    Activations Density 0.001%

    No Known Activations