© 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. 131659
    Prev
    Next
    INDEX
    Explanations

    classical physics

    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
    {
    1.27
    ized
    0.84
    ambilan
    0.79
     hemorrh
    0.78
    ية
    0.76
     reinterpret
    0.76
     {
    0.74
     v
    0.74
     เหมือน
    0.74
    ettre
    0.73
    POSITIVE LOGITS
    л
    1.27
    м
    1.22
    ز
    1.18
    م
    1.14
    i
    1.13
    の
    1.10
    이가
    1.00
    ב
    0.99
    ம்
    0.98
    ق
    0.98
    Activations Density 0.001%

    No Known Activations