© 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. 92517
    Prev
    Next
    INDEX
    Explanations

    staying nearby

    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
     Luật
    0.43
    o
    0.43
    ни
    0.40
     Hill
    0.40
    тами
    0.40
     Hills
    0.38
     But
    0.38
     nhưng
    0.37
     Gór
    0.36
     باندې
    0.35
    POSITIVE LOGITS
    ים
    0.46
     at
    0.45
    ς
    0.40
    ای
    0.38
     provenant
    0.37
    А
    0.37
    ጨማሪ
    0.37
     mencegah
    0.36
     manometer
    0.36
    ы
    0.36
    Activations Density 0.001%

    No Known Activations