© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 143
    Prev
    Next
    INDEX
    Explanations

    environmental and construction planning

    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
     unions
    0.53
     union
    0.52
    Union
    0.44
    union
    0.44
    事務
    0.44
    处理
    0.43
     ஜ
    0.43
    處理
    0.43
     Union
    0.41
     processing
    0.40
    POSITIVE LOGITS
    torn
    0.42
     torna
    0.41
     Hernandez
    0.39
     Hernández
    0.39
    ක්ෂ
    0.38
     pogod
    0.37
    ORN
    0.36
    柟
    0.36
     attachment
    0.36
     druž
    0.36
    Activations Density 0.012%

    No Known Activations