© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4884
    Prev
    Next
    INDEX
    Explanations

    `3` or punctuation

    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_40_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
    kova
    0.44
     sexto
    0.40
    mente
    0.38
    leda
    0.38
    6
    0.37
    征
    0.37
    expandindo
    0.37
     administrativa
    0.36
    strftime
    0.36
    BeforeCall
    0.36
    POSITIVE LOGITS
     commonplace
    0.39
     сосу
    0.39
     (++
    0.39
     quyền
    0.38
     سرب
    0.38
     Wrapper
    0.37
     CASCADE
    0.37
     Narrow
    0.36
     dosy
    0.36
     전류
    0.36
    Activations Density 0.024%

    No Known Activations