© 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. 19252
    Prev
    Next
    INDEX
    Explanations

    report card

    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
     সিংহ
    0.29
    m
    0.29
     प्राप्ति
    0.29
     মজা
    0.28
     Merton
    0.28
     siku
    0.28
     consideran
    0.28
    を実現
    0.28
     consideración
    0.28
     ஆராய்ச்சி
    0.27
    POSITIVE LOGITS
    TOM
    0.33
    Ｔ
    0.31
    𝚃
    0.30
    是不是
    0.29
     TOM
    0.29
     ECHO
    0.29
     T
    0.29
    塑料
    0.28
    Charles
    0.27
    道
    0.27
    Activations Density 0.002%

    No Known Activations