© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 156645
    Prev
    Next
    INDEX
    Explanations

    u or um at start of phrases

    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_2_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
    ي
    1.59
    ক
    1.50
    س
    1.48
    ك
    1.28
    ス
    1.28
    י
    1.27
    一层
    1.26
    {
    1.24
    ت
    1.22
    ра
    1.16
    POSITIVE LOGITS
    ee
    1.40
     a
    1.30
    0
    1.24
    a
    1.23
    t
    1.17
     by
    1.11
    n
    1.09
    o
    1.07
    cs
    0.98
    et
    0.97
    Activations Density 0.000%

    No Known Activations