© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214252
    Prev
    Next
    INDEX
    Explanations

    reflected light and energy

    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_5_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
    ב
    1.37
    ש
    1.32
    0
    1.28
    ン
    1.19
    น
    1.13
    н
    1.13
    л
    1.09
    ین
    1.07
    ਮ
    1.05
     appet
    1.04
    POSITIVE LOGITS
    ↵↵
    1.20
    ↵
    1.13
    ۹
    1.06
    v
    1.03
    that
    1.00
    ਾ
    0.97
    at
    0.96
    ৮
    0.95
    et
    0.94
    g
    0.93
    Activations Density 0.007%

    No Known Activations