© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 197118
    Prev
    Next
    INDEX
    Explanations

    technology brands vehicles

    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
     IUCN
    0.45
     наде
    0.44
     Rice
    0.38
     CEST
    0.38
    riel
    0.38
     jut
    0.38
     Fähigkeiten
    0.38
    栉
    0.38
     Headers
    0.37
     tég
    0.36
    POSITIVE LOGITS
    塘
    0.42
     अल्
    0.40
    bum
    0.39
    pmm
    0.39
    ysh
    0.38
    emas
    0.38
    Emma
    0.38
    aghetti
    0.38
    OHA
    0.38
    EMA
    0.37
    Activations Density 0.000%

    No Known Activations