© 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. 4188
    Prev
    Next
    INDEX
    Explanations

    how much to pay

    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
    1.41
    Money
    1.37
     Money
    1.35
    money
    1.30
     dinero
    1.21
     MONEY
    1.20
     dinheiro
    1.17
     돈
    1.10
    钱
    1.08
    เงิน
    1.07
    POSITIVE LOGITS
    what
    0.69
     what
    0.66
     чего
    0.53
     czego
    0.52
     čo
    0.49
     чого
    0.48
    What
    0.48
    什么是
    0.48
     whats
    0.47
     što
    0.47
    Activations Density 0.086%

    No Known Activations