© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44401
    Prev
    Next
    INDEX
    Explanations

    numbers, codes, and identifiers

    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_22_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
    лим
    0.44
    براير
    0.40
    ﻰ
    0.39
    íes
    0.39
    ვალ
    0.39
    珑
    0.38
    LED
    0.38
    좌
    0.38
    स्टल
    0.38
    लब
    0.38
    POSITIVE LOGITS
     american
    0.42
     TR
    0.41
     hoặc
    0.41
    滿
    0.40
     tr
    0.40
     Ok
    0.39
    $-
    0.39
     ଚ
    0.38
     nari
    0.38
     किंवा
    0.38
    Activations Density 0.009%

    No Known Activations