© 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. 176608
    Prev
    Next
    INDEX
    Explanations

    East

    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
     D
    0.46
     ತು
    0.44
    윌
    0.40
    ⃘
    0.39
     ದು
    0.39
     Antim
    0.39
    ıkl
    0.39
    Deque
    0.36
     कर्
    0.36
    মুসল
    0.36
    POSITIVE LOGITS
    治
    0.54
     East
    0.53
    East
    0.43
    east
    0.41
     emphasise
    0.38
     curing
    0.38
     Danny
    0.37
     प्रिज्म
    0.37
    Pete
    0.36
     ც
    0.36
    Activations Density 0.002%

    No Known Activations