© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 48846
    Prev
    Next
    INDEX
    Explanations

    phrases for "hello", "thank you", "sleep well"

    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_10_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
     o
    0.77
     <
    0.61
     •
    0.60
    '
    0.60
     phones
    0.60
     f
    0.59
     molds
    0.58
    い
    0.58
     ком
    0.57
    ।
    0.57
    POSITIVE LOGITS
    
    0.63
    ubwa
    0.59
    ರಿಸ
    0.58
     quét
    0.58
    us
    0.56
    ográficos
    0.56
    ष्टी
    0.56
    uré
    0.56
    <unused1840>
    0.56
    segment
    0.55
    Activations Density 0.004%

    No Known Activations