© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 212100
    Prev
    Next
    INDEX
    Explanations

    architecture

    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_43_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
    Rac
    0.40
    heated
    0.39
    不堪
    0.39
    worthiness
    0.38
     ইন্টারন্যাশনাল
    0.38
    GP
    0.38
     untenable
    0.38
    篒
    0.37
    %/
    0.37
     racemic
    0.36
    POSITIVE LOGITS
    Datum
    0.39
     Datum
    0.39
     إعادة
    0.37
     Us
    0.36
     bulging
    0.36
     Zol
    0.36
     Nation
    0.36
    agian
    0.35
     Wieder
    0.35
    ષ
    0.35
    Activations Density 0.000%

    No Known Activations