© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12424
    Prev
    Next
    INDEX
    Explanations

    letters or letter formats

    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_13_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
     imgSrc
    0.56
    Hyundai
    0.52
    сцю
    0.52
    xv
    0.52
    𝗲
    0.50
    categoryId
    0.49
    shovel
    0.49
    swa
    0.49
    ビー
    0.47
    ieger
    0.47
    POSITIVE LOGITS
     letter
    0.68
     email
    0.58
     postal
    0.56
     Letter
    0.54
     نامه
    0.53
     Children
    0.52
    牘
    0.52
     unsigned
    0.52
    Letter
    0.51
     infancia
    0.50
    Activations Density 0.012%

    No Known Activations