© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 27254
    Prev
    Next
    INDEX
    Explanations

    for public use

    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
    ಳಗ
    0.36
    ργ
    0.36
     effectués
    0.36
    豈
    0.36
     извър
    0.35
    executeUpdate
    0.35
    製造
    0.35
     انجام
    0.35
    ٱ
    0.35
    sine
    0.33
    POSITIVE LOGITS
     use
    2.59
     Use
    2.25
     использования
    2.17
    Use
    2.14
     gebruik
    2.14
     استفاده
    2.11
     использовании
    2.02
     uży
    2.00
    use
    1.99
    ใช้
    1.99
    Activations Density 0.074%

    No Known Activations