© 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
    2. Gemma-3-27B-IT
    3. 12-GEMMASCOPE-2-TRANSCODER-262K
    4. 198611
    Prev
    Next
    INDEX
    Explanations

    drawing basic lines and shapes

    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_12_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
     약
    0.54
    ל
    0.53
     lop
    0.53
     pencil
    0.52
     pencils
    0.50
     circulate
    0.49
    𝙮
    0.49
    라인
    0.49
     about
    0.48
    ئي
    0.47
    POSITIVE LOGITS
     Gummies
    0.52
     китай
    0.49
    isas
    0.48
     Khmer
    0.48
     Th
    0.47
     Lime
    0.46
     пусто
    0.46
     stesso
    0.46
     Glock
    0.46
     комплек
    0.46
    Activations Density 0.030%

    No Known Activations