© 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. 108556
    Prev
    Next
    INDEX
    Explanations

    cushioning

    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
     it
    1.09
    ва
    1.07
    yl
    1.03
     to
    0.99
     channeled
    0.88
    .¹
    0.87
     ойнотуу
    0.86
     at
    0.85
     яка
    0.85
    od
    0.85
    POSITIVE LOGITS
    ৫
    1.25
    ﺍ
    1.18
    А
    1.13
    م
    1.05
    m
    0.96
    С
    0.95
    З
    0.95
    Е
    0.94
    0.93
    G
    0.93
    Activations Density 0.000%

    No Known Activations