© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 200590
    Prev
    Next
    INDEX
    Explanations

    work and employment

    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_46_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
    录
    0.40
     নয়ন
    0.38
    neho
    0.38
    त्रि
    0.38
     proceso
    0.38
    Ꮐ
    0.38
    錄
    0.38
     ट्रिपल
    0.37
    眅
    0.35
    ุ่ม
    0.35
    POSITIVE LOGITS
     staff
    0.38
     working
    0.37
     sabbatical
    0.37
     capital
    0.37
     capitals
    0.36
    hran
    0.36
    KSprite
    0.36
     Bhub
    0.36
     buil
    0.35
    WORKING
    0.35
    Activations Density 0.002%

    No Known Activations