© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 163144
    Prev
    Next
    INDEX
    Explanations

    Duke University, Duke Energy, Duke Nukem

    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_31_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
     pijn
    0.35
    ومین
    0.33
    佷
    0.33
     parallelism
    0.33
    Apache
    0.32
    Biografia
    0.32
    ựng
    0.32
     pleg
    0.32
    裁剪
    0.32
    损
    0.32
    POSITIVE LOGITS
     Aussch
    0.39
     música
    0.36
     chacun
    0.36
     Boxing
    0.35
     Música
    0.35
     Boxer
    0.35
     duke
    0.34
    必ず
    0.34
    汤
    0.33
     높
    0.33
    Activations Density 0.000%

    No Known Activations