© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 130691
    Prev
    Next
    INDEX
    Explanations

    I

    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_50_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
     epicenter
    0.41
    আই
    0.41
    
    0.40
     bad
    0.38
     Ald
    0.38
    ји
    0.36
    Ald
    0.36
     Grower
    0.36
    ઇ
    0.35
     prejudicial
    0.35
    POSITIVE LOGITS
     הרב
    0.40
    rey
    0.38
    कु
    0.38
     بہانہ
    0.37
    Constraints
    0.37
     বস্ত
    0.37
    activité
    0.37
    грамм
    0.36
    reinforced
    0.36
     Disha
    0.35
    Activations Density 0.008%

    No Known Activations