© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 36290
    Prev
    Next
    INDEX
    Explanations

    such

    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_50_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
     Tyler
    0.50
     Kyle
    0.48
     Victor
    0.47
     Dut
    0.47
    Victor
    0.46
     Duncan
    0.45
    Kyle
    0.44
     d
    0.44
    Tyler
    0.43
     Lowry
    0.43
    POSITIVE LOGITS
     Нико
    0.40
    聡
    0.40
     Marcello
    0.39
    脉
    0.38
    مل
    0.37
     анато
    0.37
     formatter
    0.36
    ricia
    0.35
    ambda
    0.34
    টক
    0.34
    Activations Density 0.005%

    No Known Activations