© 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. 179021
    Prev
    Next
    INDEX
    Explanations

    user interface actions

    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
    jär
    0.39
     tam
    0.38
     igaz
    0.37
    polymer
    0.37
    Crawler
    0.36
     виконав
    0.36
     w
    0.36
     differentiable
    0.36
    tamil
    0.35
    ʲ
    0.35
    POSITIVE LOGITS
     Bim
    0.46
    衢
    0.39
     blacks
    0.38
     Hegel
    0.38
    ศรี
    0.38
    螺
    0.37
    ప్రదేశ
    0.37
     pastries
    0.36
     Льво
    0.36
    imek
    0.36
    Activations Density 0.000%

    No Known Activations