© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 51-GEMMASCOPE-2-TRANSCODER-262K
    4. 68517
    Prev
    Next
    INDEX
    Explanations

    AI model weights

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_51_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
    હેરા
    0.42
    တိ
    0.40
     McGregor
    0.40
    entino
    0.39
     McF
    0.38
     अ
    0.38
     കീ
    0.38
     Gross
    0.38
     भोज
    0.38
     McLean
    0.37
    POSITIVE LOGITS
    <0xB3>
    0.40
    keywords
    0.40
     Keywords
    0.39
    Kathy
    0.38
     આં
    0.38
     knn
    0.37
    Reservation
    0.36
     khẩu
    0.36
     кома
    0.35
     Kathy
    0.35
    Activations Density 0.013%

    No Known Activations