© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 34578
    Prev
    Next
    INDEX
    Explanations

    prepare, execute, calculate

    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_31_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
     பாதிக்க
    0.39
     fiber
    0.38
     позна
    0.38
     meet
    0.37
    Hg
    0.37
     पिछड़ा
    0.37
     ্
    0.36
    纤维
    0.36
     stratified
    0.36
    ेट्टी
    0.36
    POSITIVE LOGITS
    准备
    0.48
     വേണ്ടി
    0.47
     подготовлено
    0.47
    用意
    0.46
    準備
    0.46
     készült
    0.45
    prepared
    0.45
     przygot
    0.42
    prepare
    0.41
    を用意
    0.41
    Activations Density 0.018%

    No Known Activations