© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44047
    Prev
    Next
    INDEX
    Explanations

    rooftop solar, harvesting, pool, bars

    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_3_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
    mm
    0.78
    يل
    0.73
    ٣
    0.73
    J
    0.71
    м
    0.70
    V
    0.69
    ies
    0.67
    وت
    0.66
    Common
    0.66
    ij
    0.65
    POSITIVE LOGITS
     інших
    0.71
    رین
    0.70
    t
    0.69
     інші
    0.67
    halt
    0.65
     gái
    0.64
    暊
    0.64
    ক
    0.62
     superflu
    0.61
     enjoin
    0.60
    Activations Density 0.000%

    No Known Activations