© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 132065
    Prev
    Next
    INDEX
    Explanations

    caused

    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
    ,":
    0.38
    的一部分
    0.37
    हरु
    0.36
    entropic
    0.36
    িত
    0.36
    ಿತಿ
    0.36
     GÉN
    0.36
    enamefont
    0.36
     ။
    0.35
    十二章
    0.35
    POSITIVE LOGITS
     by
    0.62
     By
    0.56
    by
    0.55
    By
    0.53
     бы
    0.52
    ness
    0.50
     oleh
    0.50
     bằng
    0.48
    由
    0.48
     توسط
    0.47
    Activations Density 0.010%

    No Known Activations