© 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. 129890
    Prev
    Next
    INDEX
    Explanations

    keel, keaton, keurig, kykeon

    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
    та
    0.97
     ボタン
    0.95
    taining
    0.94
     смесь
    0.94
    ],”
    0.94
    ],
    0.93
     różne
    0.93
     dilwale
    0.90
    ta
    0.89
     время
    0.88
    POSITIVE LOGITS
    en
    1.57
    ز
    1.45
    ر
    1.24
    et
    1.03
    ل
    1.00
    em
    0.97
    د
    0.97
    с
    0.95
    ار
    0.94
    க
    0.92
    Activations Density 0.000%

    No Known Activations