© 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
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 131982
    Prev
    Next
    INDEX
    Explanations

    scrolling or scrapping

    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
    on
    1.05
    ना
    0.96
     that
    0.93
    ו
    0.93
    ра
    0.89
    و
    0.89
    ا
    0.87
    もの
    0.86
    that
    0.86
    u
    0.86
    POSITIVE LOGITS
    ى
    1.21
     repent
    0.91
    )…
    0.90
    <0x80>
    0.82
    ىسى
    0.82
    to
    0.81
     aument
    0.80
    ０
    0.77
    seekBar
    0.77
    )،
    0.77
    Activations Density 0.002%

    No Known Activations