© 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. 216878
    Prev
    Next
    INDEX
    Explanations

    noon midday

    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
     FPS
    0.43
    FPS
    0.40
     piss
    0.38
    लीप
    0.38
     Romance
    0.38
     pote
    0.37
     erode
    0.37
    ἱ
    0.37
     Ulysses
    0.37
     atk
    0.36
    POSITIVE LOGITS
     ظ
    1.46
     الظ
    1.41
    ظ
    1.24
     ظاهر
    1.14
     Zah
    1.01
    ﻈ
    0.99
     Dh
    0.95
    appear
    0.94
    Appear
    0.93
     zah
    0.91
    Activations Density 0.001%

    No Known Activations