© 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. 211053
    Prev
    Next
    INDEX
    Explanations

    rulers and monarchs

    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
     পদ্ধতি
    0.48
     কেবলমাত্র
    0.45
    obarbital
    0.45
     userDao
    0.44
    糬
    0.43
     가족
    0.42
    enderita
    0.42
    gadas
    0.42
    舏
    0.41
    গ্রস্ত
    0.41
    POSITIVE LOGITS
     negotiated
    0.44
    Views
    0.44
    ranking
    0.43
     '!
    0.42
    rate
    0.41
     Images
    0.40
     !
    0.40
    Images
    0.40
    (";
    0.39
     !"
    0.38
    Activations Density 0.001%

    No Known Activations