© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    4. 198077
    Prev
    Next
    INDEX
    Explanations

    when

    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
    )}},
    0.39
     evacuate
    0.38
     Kry
    0.37
    機器
    0.36
    iply
    0.36
    த்துவ
    0.36
     pala
    0.36
    컴
    0.36
    It
    0.36
     differentiate
    0.35
    POSITIVE LOGITS
    विद
    0.39
    ده
    0.39
    ೊಂದಿಗೆ
    0.39
    &$\
    0.38
     Божи
    0.38
     Ascension
    0.36
    Bk
    0.35
    企业的
    0.35
    apon
    0.34
    ණ
    0.34
    Activations Density 0.005%

    No Known Activations