© 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. 46765
    Prev
    Next
    INDEX
    Explanations

    triggering events

    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
    ق
    0.19
    ف
    0.19
    ব
    0.17
    ب
    0.17
    b
    0.17
    قوم
    0.16
    o
    0.16
    мот
    0.16
    דם
    0.15
     Goshen
    0.15
    POSITIVE LOGITS
    ların
    0.19
    am
    0.18
     خیلی
    0.17
    る
    0.17
    ku
    0.16
    ėtų
    0.16
    rao
    0.16
    ulo
    0.16
    มัน
    0.16
    iela
    0.16
    Activations Density 0.001%

    No Known Activations