© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 122634
    Prev
    Next
    INDEX
    Explanations

    Dupont, Dublin, Durometer, Doubanjiang, Cowboys

    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_3_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
    ंतर
    0.71
     Subsidi
    0.62
    га
    0.62
    improve
    0.62
     menurun
    0.62
    ]。
    0.60
    ран
    0.59
    broccoli
    0.59
    一系列
    0.58
    зья
    0.58
    POSITIVE LOGITS
     is
    0.85
    ↵↵
    0.76
     ऐसा
    0.74
    ндекс
    0.71
    U
    0.71
     }
    0.70
    з
    0.66
    ul
    0.66
    他
    0.65
    ל
    0.64
    Activations Density 0.003%

    No Known Activations