© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39615
    Prev
    Next
    INDEX
    Explanations

    time and duration

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    先行
    0.47
    先の
    0.43
    Sapp
    0.42
    先
    0.41
     rear
    0.40
    行く
    0.40
    嗣
    0.39
    此
    0.39
    宜
    0.39
    뒷
    0.38
    POSITIVE LOGITS
     lần
    0.39
    欠
    0.38
     yaşı
    0.36
    泡
    0.36
    idas
    0.36
     onCreate
    0.36
    onCreate
    0.36
    ühle
    0.35
    ಂಗ್ರೆ
    0.35
     ಕಿ
    0.35
    Activations Density 0.002%

    No Known Activations