© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210829
    Prev
    Next
    INDEX
    Explanations

    geographical regions and administrative divisions

    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_20_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
    ----------------
    0.45
     d
    0.41
     Inst
    0.39
     Whit
    0.38
     !!!
    0.38
       
    0.37
     )
    0.37
     Worth
    0.37
     !!
    0.37
     ")
    0.37
    POSITIVE LOGITS
    仿佛
    0.42
     réunion
    0.42
    𝜌
    0.41
    ₹
    0.41
    কাতে
    0.41
    уч
    0.41
    厙
    0.41
    ্যাম্প
    0.41
     شكله
    0.40
     क्वाड्रेटिक
    0.40
    Activations Density 0.000%

    No Known Activations