© 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. 199488
    Prev
    Next
    INDEX
    Explanations

    training

    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
     utbild
    0.43
     eğitimi
    0.43
    簫
    0.41
     Klik
    0.38
    াদিগকে
    0.38
    駁
    0.37
     पाठ्यक्रम
    0.37
     ބ
    0.37
     Pendidikan
    0.37
     opleiding
    0.37
    POSITIVE LOGITS
     entra
    0.75
     entraîne
    0.70
     ant
    0.70
     entraî
    0.68
     entraîner
    0.61
     entren
    0.60
    entraînement
    0.57
    Ent
    0.55
     Ent
    0.55
     allen
    0.54
    Activations Density 0.000%

    No Known Activations