© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 6333
    Prev
    Next
    INDEX
    Explanations

    ```python`, `try...except` blocks

    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
    pir
    0.29
    ["
    0.29
    ection
    0.28
    ቀት
    0.28
    --“
    0.28
    {"
    0.27
    mbox
    0.27
    Royal
    0.27
    Cho
    0.27
    サスカ
    0.27
    POSITIVE LOGITS
     Tej
    0.27
     peoples
    0.26
    τος
    0.26
     arenas
    0.26
    }$&$-
    0.26
     През
    0.26
     Whether
    0.25
    arları
    0.25
     catt
    0.25
     metri
    0.25
    Activations Density 0.024%

    No Known Activations