© 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. 39733
    Prev
    Next
    INDEX
    Explanations

    at your convenience

    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
     调用
    0.70
     项目
    0.68
     環境
    0.65
     让
    0.64
     应用
    0.64
     อื่น
    0.63
     を
    0.62
     过
    0.62
     غير
    0.61
     武田
    0.61
    POSITIVE LOGITS
     improving
    0.64
     the
    0.59
    lt
    0.58
     improves
    0.57
    æk
    0.55
    ith
    0.55
     \
    0.55
     experts
    0.52
     ausreiche
    0.52
    iths
    0.52
    Activations Density 0.002%

    No Known Activations