© 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
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 228369
    Prev
    Next
    INDEX
    Explanations

    say 0s and 1s

    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_57_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
     మా
    0.38
     sciences
    0.34
    individu
    0.34
     ਵਰ
    0.34
    自己的
    0.32
    ထ
    0.32
    ConformanceMode
    0.32
     eigenen
    0.32
     defecto
    0.32
     defect
    0.31
    POSITIVE LOGITS
    湋
    0.35
    ósito
    0.35
     sepd
    0.34
    locationY
    0.34
    banam
    0.34
     reinado
    0.34
    ôr
    0.34
    ͑
    0.34
    ][%
    0.33
    ವಲ್ಲ
    0.33
    Activations Density 0.001%

    No Known Activations