© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88958
    Prev
    Next
    INDEX
    Explanations

    code snippets, html, programming

    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_3_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
    ти
    1.07
    в
    0.78
    Caching
    0.71
    й
    0.68
    ור
    0.67
    ၁
    0.66
    .’’
    0.66
    ስ
    0.66
    Puede
    0.65
    Sear
    0.65
    POSITIVE LOGITS
     from
    0.77
    )
    0.68
     are
    0.68
     ist
    0.65
     million
    0.65
    um
    0.65
     with
    0.64
     que
    0.63
    t
    0.63
    ak
    0.63
    Activations Density 0.003%

    No Known Activations