© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60119
    Prev
    Next
    INDEX
    Explanations

    Northern regions and Italy

    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_11_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
    Mediterranean
    0.57
     Mediterranean
    0.56
    ي
    0.48
    Italian
    0.45
    Italy
    0.45
     Mediterr
    0.45
     mediterr
    0.44
    S
    0.43
    ل
    0.43
    Win
    0.42
    POSITIVE LOGITS
     அகற்ற
    0.44
    🏧
    0.43
     খেলা
    0.43
     suction
    0.42
     khán
    0.42
     захід
    0.41
     resistência
    0.41
     lymphatic
    0.41
     спортс
    0.41
     carinatis
    0.41
    Activations Density 0.029%

    No Known Activations