© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 223688
    Prev
    Next
    INDEX
    Explanations

    two followed by digits or years

    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
    2
    0.42
     و
    0.38
     by
    0.37
    using
    0.37
    B
    0.36
    нули
    0.36
    4
    0.36
     be
    0.35
     и
    0.35
    <b>
    0.35
    POSITIVE LOGITS
    dding
    0.38
    ល្អ
    0.36
     misalignment
    0.36
     มัน
    0.35
     jira
    0.35
    d
    0.35
    <unused693>
    0.35
     buckling
    0.34
     ذریع
    0.34
    ने
    0.34
    Activations Density 0.004%

    No Known Activations