© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 208619
    Prev
    Next
    INDEX
    Explanations

    Villa d'Este, Unité d'Habitation

    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_10_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
    t
    0.39
    timer
    0.28
    layered
    0.26
     ledger
    0.25
     by
    0.25
    neath
    0.24
    ปี
    0.24
    hack
    0.24
     learner
    0.24
     Saving
    0.24
    POSITIVE LOGITS
    ي
    0.36
    Zespół
    0.35
    Ż
    0.34
    Č
    0.33
    Ο
    0.32
    vět
    0.32
    Woh
    0.31
    Gü
    0.31
    ।'
    0.31
     zů
    0.31
    Activations Density 0.002%

    No Known Activations