© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14034
    Prev
    Next
    INDEX
    Explanations

    Marcos, Gandhi, politicians

    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_13_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
     can
    0.54
    Soccer
    0.54
    St
    0.51
    Ginger
    0.51
    د
    0.50
    Mary
    0.50
    ώ
    0.50
    Ware
    0.48
    Gaia
    0.48
    D
    0.48
    POSITIVE LOGITS
     اكتوبر
    0.58
     Presidential
    0.52
    必须要
    0.52
    လိုအပ်
    0.51
     اي
    0.50
     kaks
    0.48
     позд
    0.48
    appointed
    0.48
    ınızı
    0.48
     대통령
    0.47
    Activations Density 0.001%

    No Known Activations