© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 29712
    Prev
    Next
    INDEX
    Explanations

    text HOME

    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_10_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
     text
    0.89
    文本
    0.86
    。
    0.84
    Text
    0.82
    TextChanged
    0.77
     текст
    0.74
     文字
    0.72
     Text
    0.70
     Texts
    0.70
     نص
    0.69
    POSITIVE LOGITS
    ied
    0.98
    -
    0.95
    ien
    0.93
    ling
    0.89
    li
    0.81
    lier
    0.81
    ls
    0.79
     दुःख
    0.79
    le
    0.79
    िंग
    0.78
    Activations Density 0.052%

    No Known Activations