© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4843
    Prev
    Next
    INDEX
    Explanations

    game loop after fill

    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_40_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
    卩
    0.41
    कत
    0.38
     interchanges
    0.38
    {\$
    0.38
    alkoz
    0.37
     Кол
    0.37
     .\
    0.36
     penn
    0.36
     dispon
    0.35
     مركز
    0.35
    POSITIVE LOGITS
    泯
    0.38
    ხედ
    0.36
    expo
    0.36
    Version
    0.35
     Trans
    0.35
     Schottky
    0.35
    展示
    0.34
    かず
    0.34
    グッズ
    0.34
     Visualization
    0.34
    Activations Density 0.011%

    No Known Activations