© 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. 36445
    Prev
    Next
    INDEX
    Explanations

    inner content

    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
    обходи
    0.38
    妿
    0.35
    ODY
    0.35
    блиоте
    0.35
    ardan
    0.34
     الطريق
    0.34
     अड्डा
    0.33
    lli
    0.33
    िना
    0.33
     odu
    0.33
    POSITIVE LOGITS
    内
    2.28
     nội
    2.25
    內
    2.17
     内
    1.98
    내
    1.88
     Nội
    1.77
     iç
    1.74
     inner
    1.66
     Inner
    1.58
    Inner
    1.57
    Activations Density 0.003%

    No Known Activations