© 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. 6363
    Prev
    Next
    INDEX
    Explanations

    1-2 pounds per week

    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
     money
    0.89
    Money
    0.81
    money
    0.77
     Money
    0.76
     돈
    0.76
     dinheiro
    0.75
     dinero
    0.72
     MONEY
    0.71
     geld
    0.70
    錢
    0.70
    POSITIVE LOGITS
     ድረስ
    0.39
    )')
    0.39
    ocell
    0.38
    📧
    0.37
    上网
    0.36
    াওয়া
    0.35
    wake
    0.35
     վ
    0.34
    ',)
    0.34
     Parenting
    0.34
    Activations Density 0.000%

    No Known Activations