© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 157050
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_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
    ו
    1.70
    و
    1.55
    ا
    1.47
    б
    1.41
    م
    1.39
    т
    1.30
    ج
    1.27
    ليل
    1.18
    كيف
    1.16
    اريخ
    1.16
    POSITIVE LOGITS
    ning
    1.14
     for
    1.11
     with
    1.09
    ine
    1.08
     to
    1.05
    upuncture
    1.05
    ing
    1.03
    ۰
    1.01
     it
    0.97
    ase
    0.96
    Activations Density 0.000%

    No Known Activations