© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31845
    Prev
    Next
    INDEX
    Explanations

    programming code

    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_50_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
    主管部门
    0.29
    չ
    0.29
    Indexes
    0.29
    찬
    0.29
    ]=\
    0.28
    Coastal
    0.28
     فوج
    0.28
     ремонта
    0.28
    ום
    0.28
     составляет
    0.28
    POSITIVE LOGITS
     Trujillo
    0.47
     semnific
    0.41
    <unused693>
    0.40
     warfarin
    0.38
    <unused195>
    0.38
     Marquette
    0.38
     उपसर्ग
    0.38
     clarinet
    0.38
    <unused361>
    0.37
    ifstream
    0.37
    Activations Density 0.002%

    No Known Activations