© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57298
    Prev
    Next
    INDEX
    Explanations

    in case of

    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_11_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
    計算
    0.54
    衣服
    0.53
    言語
    0.52
    建筑物
    0.51
    身体
    0.50
    将
    0.50
    امات
    0.50
    깅
    0.50
     El
    0.50
    بعد
    0.49
    POSITIVE LOGITS
     kısmı
    0.68
     fêtes
    0.64
     λό
    0.62
    êne
    0.62
     muitos
    0.61
     baisse
    0.60
     sürec
    0.59
    ần
    0.59
    یا
    0.59
     önemli
    0.58
    Activations Density 0.000%

    No Known Activations