© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 225479
    Prev
    Next
    INDEX
    Explanations

    hazmat suits

    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
    د
    0.79
    ร
    0.78
    رك
    0.65
    ية
    0.63
    密的
    0.63
    {
    0.63
    }=
    0.62
    رس
    0.61
    ль
    0.61
    ئ
    0.61
    POSITIVE LOGITS
    uatu
    0.80
     підпри
    0.78
     paramedic
    0.73
    amaran
    0.72
    izability
    0.71
     семь
    0.69
     poter
    0.67
     shipper
    0.67
     हरित
    0.65
     foal
    0.64
    Activations Density 0.001%

    No Known Activations