© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14834
    Prev
    Next
    INDEX
    Explanations

    strategic agendas and initiatives

    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_15_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
    utar
    0.51
     topographical
    0.50
    थन
    0.50
     ensinar
    0.50
     navegar
    0.49
     kullanılır
    0.49
    苋
    0.49
    ేక
    0.48
     démontrer
    0.48
     తయ
    0.47
    POSITIVE LOGITS
     ত
    0.55
    LORD
    0.52
     His
    0.51
    রুদ্ধ
    0.49
    了一眼
    0.49
    ټر
    0.49
    ibold
    0.48
     ankles
    0.48
     \
    0.48
    ovno
    0.47
    Activations Density 0.008%

    No Known Activations