© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37900
    Prev
    Next
    INDEX
    Explanations

    Portuguese place names and events

    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_11_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
     sandal
    0.55
     aldehyde
    0.55
    ן
    0.54
     cacao
    0.53
    షా
    0.53
    론
    0.52
     filo
    0.51
     camel
    0.50
     condiment
    0.50
     idol
    0.48
    POSITIVE LOGITS
    woofer
    0.60
    director
    0.56
    iiv
    0.54
    d
    0.54
     Adapted
    0.52
     একজন
    0.52
     اړه
    0.52
    NEW
    0.50
     Testing
    0.50
    estimated
    0.50
    Activations Density 0.012%

    No Known Activations