© 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. 175610
    Prev
    Next
    INDEX
    Explanations

    Scripts

    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
    ("'
    0.35
     দিনাজপুর
    0.33
    Alberta
    0.33
    ("[
    0.32
    想定
    0.32
    wci
    0.31
    િયન
    0.31
    ্সা
    0.31
     स्त्रीलिंग
    0.31
    ('/:
    0.31
    POSITIVE LOGITS
     paves
    0.41
    Tá
    0.36
    roves
    0.36
     פס
    0.36
    ès
    0.35
     Prisma
    0.35
     lähe
    0.35
    jà
    0.34
    untary
    0.34
     prens
    0.34
    Activations Density 0.001%

    No Known Activations