© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35861
    Prev
    Next
    INDEX
    Explanations

    brewhouse, CA, 1

    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_3_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
     quaternary
    0.75
    ৮
    0.68
     stimulation
    0.67
     tribute
    0.67
     tuition
    0.67
     terminó
    0.67
     y
    0.66
     neuroscience
    0.66
     simulator
    0.65
     powerhouse
    0.65
    POSITIVE LOGITS
    ى
    1.01
    к
    0.79
    1
    0.70
    ین
    0.69
    лся
    0.68
    o
    0.67
    ри
    0.65
    e
    0.65
    ль
    0.64
    ю
    0.63
    Activations Density 0.001%

    No Known Activations