© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 105322
    Prev
    Next
    INDEX
    Explanations

    solar information

    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_1_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
    人
    1.48
    te
    1.38
    ने
    1.27
    ad
    1.23
    ра
    1.20
    在
    1.12
    t
    1.08
    ne
    0.99
    le
    0.97
    la
    0.97
    POSITIVE LOGITS
    0
    1.30
     that
    1.09
    ų
    1.05
    was
    1.04
     was
    0.96
    י
    0.95
    και
    0.93
    
    0.93
     کې
    0.93
    ھوں
    0.90
    Activations Density 0.003%

    No Known Activations