© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242157
    Prev
    Next
    INDEX
    Explanations

    will happen

    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_40_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
     executes
    0.44
     execute
    0.41
    execute
    0.40
     wykon
    0.39
     ausgeführt
    0.39
    伖
    0.38
     تنفيذ
    0.38
    执行
    0.38
    制作
    0.38
    જો
    0.38
    POSITIVE LOGITS
    ugat
    0.37
     wipers
    0.37
    गम
    0.36
    ܘܢ
    0.35
     induc
    0.34
    ômes
    0.34
     perch
    0.34
    ivy
    0.34
     underlined
    0.34
    蔭
    0.34
    Activations Density 0.001%

    No Known Activations