© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 198265
    Prev
    Next
    INDEX
    Explanations

    git submodules or Vundle

    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_15_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
    ک
    0.58
    k
    0.57
    f
    0.56
    Well
    0.54
    ก
    0.52
    Т
    0.52
    own
    0.50
    Ш
    0.50
    Les
    0.50
    akes
    0.49
    POSITIVE LOGITS
     빙
    0.54
    鲟
    0.52
     заповед
    0.51
    প্রিল
    0.50
    supportsFocus
    0.50
    덬
    0.50
    itando
    0.49
    砝
    0.49
     跳转
    0.48
    <unused1059>
    0.48
    Activations Density 0.002%

    No Known Activations