© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 32766
    Prev
    Next
    INDEX
    Explanations

    YouTube video

    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_7_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
     are
    1.12
     to
    1.00
    yl
    0.96
    ara
    0.94
     be
    0.89
     =
    0.84
     o
    0.83
    )
    0.82
     ৪
    0.80
    \
    0.80
    POSITIVE LOGITS
    اس
    0.71
    ن
    0.70
    그
    0.66
    無
    0.66
    或者
    0.65
     दट
    0.64
    最低
    0.64
    虽然
    0.64
     preload
    0.64
    ১৪
    0.63
    Activations Density 0.007%

    No Known Activations