© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 2061
    Prev
    Next
    INDEX
    Explanations

    URLs and code definitions

    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
    JD
    0.32
    mitz
    0.32
    ឹ
    0.32
    chluss
    0.32
     Yud
    0.32
    reibung
    0.31
    pperware
    0.31
    FOR
    0.31
    łaszcza
    0.31
    hagen
    0.30
    POSITIVE LOGITS
    佸
    0.37
     Си
    0.35
    चित
    0.34
    Си
    0.33
    ismod
    0.33
     Conducting
    0.33
     स्व
    0.33
     atraves
    0.32
     проводить
    0.32
    বন্ধন
    0.31
    Activations Density 0.020%

    No Known Activations