© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 29754
    Prev
    Next
    INDEX
    Explanations

    yield savings account

    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
    spl
    0.39
     Littleton
    0.38
     simplices
    0.38
     pembangunan
    0.37
    isomer
    0.36
     единица
    0.36
    Ẽ
    0.36
    そも
    0.35
     adaptación
    0.35
    ql
    0.35
    POSITIVE LOGITS
    ృత
    0.38
     حرف
    0.37
    Handle
    0.36
     profes
    0.36
    ارف
    0.35
    :{
    0.35
     tar
    0.35
    ومات
    0.35
     :{
    0.35
    SK
    0.35
    Activations Density 0.021%

    No Known Activations