© 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. 64680
    Prev
    Next
    INDEX
    Explanations

    China and regions

    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
    South
    0.48
     South
    0.47
     Southern
    0.40
    SOUTH
    0.40
    千
    0.39
     南
    0.39
     Schum
    0.38
     solar
    0.38
     ListItem
    0.38
    
    0.37
    POSITIVE LOGITS
     enthalpy
    0.43
    toLowerCase
    0.39
    Фа
    0.39
     explotación
    0.37
    ^*_{
    0.36
     reproduced
    0.36
    僧
    0.36
     настоящее
    0.36
     funcionalidad
    0.35
    ジャパン
    0.35
    Activations Density 0.009%

    No Known Activations