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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 162631
    Prev
    Next
    INDEX
    Explanations

    function main 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_31_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
    Etudes
    0.37
    每年
    0.37
    stel
    0.36
    telling
    0.35
    exposure
    0.34
    Tempo
    0.34
    驁
    0.34
    Qualification
    0.34
    steen
    0.33
    Setting
    0.33
    POSITIVE LOGITS
     typed
    0.38
     equals
    0.37
    ับสน
    0.36
    ிகளைக்
    0.36
    滚
    0.35
    iennent
    0.35
    维生素
    0.35
    Supplier
    0.35
     rolling
    0.34
     scrolls
    0.34
    Activations Density 0.003%

    No Known Activations