© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 37878
    Prev
    Next
    INDEX
    Explanations

    flowers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    rabbitmq
    0.39
    ๛
    0.37
    ້ນ
    0.36
     regretted
    0.36
    mie
    0.36
     پرو
    0.35
     Vino
    0.35
    Lack
    0.35
    MyToolkit
    0.34
    ütz
    0.34
    POSITIVE LOGITS
    花
    0.58
     flower
    0.57
     thư
    0.56
     hoa
    0.56
     花
    0.54
     Flower
    0.51
     हाँ
    0.50
    Flower
    0.50
     ses
    0.49
     sa
    0.48
    Activations Density 0.000%

    No Known Activations