© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 140308
    Prev
    Next
    INDEX
    Explanations

    TV shows named after people

    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
    gg
    0.54
    taa
    0.54
    ازت
    0.54
    duh
    0.54
    ด
    0.52
    ล
    0.51
    medicine
    0.51
    avista
    0.49
     wouldn
    0.49
     successor
    0.49
    POSITIVE LOGITS
     señalar
    0.55
     technische
    0.52
     incluyendo
    0.50
    рово
    0.49
    䏍
    0.49
     pero
    0.49
    包括
    0.49
     señala
    0.49
     señaló
    0.47
     кварта
    0.46
    Activations Density 0.000%

    No Known Activations