© 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. 6894
    Prev
    Next
    INDEX
    Explanations

    United States, USA, English

    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
     '}';
    0.43
    ouncement
    0.38
     precedes
    0.38
     bb
    0.37
    issner
    0.36
    eredReader
    0.36
    ือก
    0.36
    ="/"
    0.35
    واره
    0.35
    ம்ப
    0.35
    POSITIVE LOGITS
     United
    1.19
    United
    1.15
     यूनाइटेड
    0.88
     США
    0.86
     UNITED
    0.86
     USA
    0.84
    UNITED
    0.84
     Verenigde
    0.82
     US
    0.80
    สห
    0.79
    Activations Density 0.121%

    No Known Activations