© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 164008
    Prev
    Next
    INDEX
    Explanations

    Start of parenthesis or reading

    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_31_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
     plugged
    0.35
     JavaVersion
    0.35
    tikzpicture
    0.34
     backed
    0.33
     secured
    0.32
     כמ
    0.32
     Secured
    0.32
    厭
    0.32
     instrumental
    0.32
     напо
    0.32
    POSITIVE LOGITS
    鹑
    0.35
     bienvenue
    0.34
     সম্মান
    0.34
     पुष्प
    0.34
    glBind
    0.33
    चीनी
    0.33
     आवाहन
    0.32
    鍏
    0.32
    बिया
    0.32
     পূর্ণ
    0.31
    Activations Density 0.001%

    No Known Activations