© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14407
    Prev
    Next
    INDEX
    Explanations

    epoch in range

    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_40_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
     暗
    0.29
     ગા
    0.28
     Tenn
    0.24
     AFI
    0.24
    imageList
    0.24
    External
    0.24
    ogt
    0.23
    暗
    0.23
     म्हणा
    0.23
     footprints
    0.23
    POSITIVE LOGITS
     dermat
    0.29
    EOS
    0.27
     EOS
    0.27
     bru
    0.26
    oshin
    0.26
     अगला
    0.26
     Radi
    0.26
    ন্দ্র
    0.26
     radiological
    0.26
     पुरात
    0.25
    Activations Density 0.001%

    No Known Activations