© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 127210
    Prev
    Next
    INDEX
    Explanations

    slideshows and sliders

    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_37_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
    ៣
    0.40
    serializing
    0.40
    ıştı
    0.39
     തുറ
    0.38
     инвали
    0.38
     hues
    0.38
     Bakufu
    0.38
     almacenar
    0.38
    佞
    0.38
    志愿者
    0.37
    POSITIVE LOGITS
     slides
    0.68
     slide
    0.62
    Slides
    0.57
     Slides
    0.56
    slides
    0.55
    Slide
    0.55
    slide
    0.51
     Slide
    0.50
    Optimization
    0.43
     slid
    0.42
    Activations Density 0.002%

    No Known Activations