© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130752
    Prev
    Next
    INDEX
    Explanations

    try ( or try

    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
     in
    1.14
    1.08
    。
    0.93
    ى
    0.90
     In
    0.88
    も
    0.78
    ।
    0.75
    0.73
     &
    0.72
    $.
    0.72
    POSITIVE LOGITS
    quela
    1.03
    ్ఞ
    1.00
    ла
    0.99
    ato
    0.98
     Após
    0.98
    ه
    0.98
    ங்க
    0.97
    out
    0.96
    на
    0.96
    ud
    0.95
    Activations Density 0.008%

    No Known Activations