© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 5186
    Prev
    Next
    INDEX
    Explanations

    demonstrates how

    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_38_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
    href
    0.40
    ಹೆ
    0.38
     полной
    0.37
     път
    0.37
     condense
    0.37
     dyes
    0.36
    WHY
    0.36
    ++){
    0.36
     ++
    0.35
    drugs
    0.35
    POSITIVE LOGITS
     cómo
    0.72
     ఎలా
    0.71
     nasıl
    0.70
     ಹೇ
    0.68
     how
    0.66
     എങ്ങനെ
    0.65
     어떻게
    0.64
     எப்படி
    0.62
    How
    0.61
     what
    0.60
    Activations Density 0.010%

    No Known Activations