© 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. 202997
    Prev
    Next
    INDEX
    Explanations

    historical China

    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
     Noble
    0.59
     noble
    0.55
    noble
    0.52
    贵
    0.51
    Noble
    0.50
     nobleman
    0.50
    貴
    0.49
    贵的
    0.47
    AP
    0.45
     Nob
    0.43
    POSITIVE LOGITS
     менедж
    0.42
     system
    0.42
     भए
    0.38
    etre
    0.38
     системе
    0.38
    amata
    0.37
     clinics
    0.37
     administrativos
    0.37
     सिक्स
    0.37
    ೬
    0.36
    Activations Density 0.001%

    No Known Activations