© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 197579
    Prev
    Next
    INDEX
    Explanations

    by

    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
    ंडा
    0.43
    ں
    0.40
    лай
    0.40
     definition
    0.37
    ವಾಗ
    0.36
     ws
    0.36
    LLING
    0.36
     ಕಾರಣ
    0.35
    gs
    0.35
    CTIONS
    0.35
    POSITIVE LOGITS
    imia
    0.40
     algunas
    0.40
    乍
    0.39
     አንዳንድ
    0.39
    toni
    0.38
    ട്ടുള്ള
    0.38
    ctg
    0.38
    tem
    0.37
     الآن
    0.37
    वाज
    0.37
    Activations Density 0.003%

    No Known Activations