© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231112
    Prev
    Next
    INDEX
    Explanations

    energy levels

    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_6_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
    ill
    0.76
    arati
    0.73
    에요
    0.73
     (
    0.73
     messa
    0.71
    mo
    0.68
    PRS
    0.66
    crafted
    0.64
    र्स
    0.64
    ین
    0.62
    POSITIVE LOGITS
    ↵↵
    1.13
    و
    1.06
    د
    0.96
    ан
    0.83
    ä
    0.82
    ו
    0.80
    ४
    0.76
    ي
    0.71
     wichtig
    0.71
    д
    0.71
    Activations Density 0.006%

    No Known Activations