© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 17549
    Prev
    Next
    INDEX
    Explanations

    分类标题

    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_34_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
     대통령
    0.49
    自動車
    0.46
    黉
    0.44
     正規
    0.44
     높은
    0.42
    ліз
    0.42
    뇌
    0.41
     complementing
    0.41
    지역
    0.41
     Lufthansa
    0.40
    POSITIVE LOGITS
    从
    0.52
    对
    0.51
    在
    0.50
    跟
    0.49
    使用了
    0.48
    把
    0.47
    一个
    0.47
    提到
    0.46
    应
    0.46
    插
    0.45
    Activations Density 0.002%

    No Known Activations