© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174680
    Prev
    Next
    INDEX
    Explanations

    numbers and percentages

    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
    гель
    0.44
    ंगामा
    0.40
    ুদ
    0.40
    }$).
    0.39
    個
    0.39
    speedboat
    0.38
    hamento
    0.38
    нах
    0.37
    يان
    0.37
    নাট
    0.37
    POSITIVE LOGITS
     :
    0.46
     [.
    0.42
     stev
    0.42
     so
    0.41
     chas
    0.41
     পড়বে
    0.40
     amongst
    0.39
     zij
    0.39
    ovil
    0.39
     ਘ
    0.39
    Activations Density 0.000%

    No Known Activations