© 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. 209960
    Prev
    Next
    INDEX
    Explanations

    Klondike, bucket

    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
    ne
    1.71
    a
    1.31
     in
    1.20
     (
    1.20
    class
    1.12
    by
    1.03
    function
    1.02
    SA
    1.00
    ution
    0.99
    <h2>
    0.98
    POSITIVE LOGITS
    ین
    1.64
    ле
    1.44
    ку
    1.43
    ні
    1.42
    트
    1.38
    지
    1.37
    يب
    1.30
    ло
    1.30
    ت
    1.29
    تي
    1.24
    Activations Density 0.000%

    No Known Activations