© 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. 132842
    Prev
    Next
    INDEX
    Explanations

    educational institutions

    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
     תי
    0.51
    immon
    0.40
    啖
    0.38
    ポーツ
    0.38
     portfolio
    0.38
     aromatic
    0.37
    etrain
    0.36
    যন্ত্র
    0.35
     stitch
    0.35
     PORT
    0.35
    POSITIVE LOGITS
     ಉದ್ದ
    0.43
     Gyne
    0.41
     kane
    0.41
     kaldı
    0.40
    જા
    0.40
    $.;
    0.39
     sanguí
    0.38
     بزر
    0.38
     volumen
    0.38
    ജി
    0.37
    Activations Density 0.000%

    No Known Activations