© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 6633
    Prev
    Next
    INDEX
    Explanations

    travel plan India Sri Lanka China Europe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     complesso
    0.42
     المرحله
    0.42
    Ground
    0.40
     complexe
    0.39
    Fat
    0.39
    Kelly
    0.38
    漕
    0.38
     পাকিস্তানীরা
    0.38
    Jake
    0.37
    )=(-
    0.37
    POSITIVE LOGITS
     అను
    0.40
     responsables
    0.40
    nee
    0.39
     processing
    0.38
     Custom
    0.38
     customs
    0.37
    主管
    0.36
     responsáveis
    0.36
     experience
    0.36
     uns
    0.36
    Activations Density 0.032%

    No Known Activations