© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 205989
    Prev
    Next
    INDEX
    Explanations

    um, ure, ads, لك, os

    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_6_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
     It
    0.99
    将
    0.95
    ना
    0.91
     an
    0.89
     in
    0.89
    เป็น
    0.89
     e
    0.86
    ۰
    0.86
    ر
    0.85
    Α
    0.83
    POSITIVE LOGITS
    p
    1.26
    6
    1.02
    ach
    0.98
    رك
    0.98
    رت
    0.98
    تي
    0.96
    SI
    0.96
    ovány
    0.94
    را
    0.93
    oo
    0.93
    Activations Density 0.000%

    No Known Activations