© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 215310
    Prev
    Next
    INDEX
    Explanations

    Seville and Spain

    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_5_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
    ار
    1.13
    عي
    1.12
    اد
    0.99
    تش
    0.98
    انا
    0.97
    াই
    0.97
    s
    0.96
    اس
    0.95
    عت
    0.95
    تها
    0.94
    POSITIVE LOGITS
    า
    1.33
    म
    1.23
     présente
    1.13
    ۔
    1.13
     активность
    1.13
    м
    1.12
     основной
    1.10
     טוב
    1.09
     cuadrada
    1.08
    в
    1.08
    Activations Density 0.000%

    No Known Activations