© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 204704
    Prev
    Next
    INDEX
    Explanations

    claimed statements or facts

    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_6_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
    ﺭ
    1.00
    он
    0.95
    ﻜ
    0.94
     veřej
    0.91
    ﺔ
    0.91
    ﻊ
    0.91
     ລັບ
    0.90
     خدمة
    0.88
    我们要
    0.87
     zaidi
    0.86
    POSITIVE LOGITS
    ल
    1.98
    is
    1.74
    л
    1.64
    د
    1.43
    ל
    1.41
    an
    1.25
    स
    1.25
    in
    1.18
    I
    1.18
    ش
    1.10
    Activations Density 0.001%

    No Known Activations