© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 3038
    Prev
    Next
    INDEX
    Explanations

    Turkish and Turkey related terms

    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_40_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
     TNumber
    0.41
     SUBSTITUTE
    0.40
    |=\
    0.40
    ផ្ទ
    0.39
    syllabus
    0.39
     iā
    0.38
     paulo
    0.38
    ቲ
    0.38
     SMITH
    0.38
    ggio
    0.37
    POSITIVE LOGITS
     Turkish
    0.96
     Istanbul
    0.87
     Turkey
    0.86
     Erdogan
    0.85
     turkish
    0.85
    Istanbul
    0.81
    Turkish
    0.80
    Turkey
    0.79
     Turks
    0.77
     Türkiye
    0.76
    Activations Density 0.016%

    No Known Activations