© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110147
    Prev
    Next
    INDEX
    Explanations

    laughter

    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
    नं
    1.11
     ਅਤੇ
    1.03
    ната
    1.02
    я
    1.02
    land
    1.02
    uts
    1.02
    '
    1.01
    st
    1.00
    ak
    1.00
    nessy
    0.99
    POSITIVE LOGITS
     be
    1.37
     a
    1.34
    т
    1.29
    ير
    1.27
    다
    1.27
    ক
    1.24
    ট
    1.19
     as
    1.16
    ত
    1.16
     will
    1.14
    Activations Density 0.001%

    No Known Activations