© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 164723
    Prev
    Next
    INDEX
    Explanations

    ol am

    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
     auditions
    0.23
     Paral
    0.22
     lake
    0.21
    츈
    0.21
    autas
    0.21
    kach
    0.20
    khart
    0.20
     late
    0.20
    ちなみに
    0.20
     percents
    0.19
    POSITIVE LOGITS
     প্রদর্শন
    0.22
     görünt
    0.22
     ///
    0.22
     سف
    0.22
    部署
    0.22
     карбо
    0.21
     تطبيق
    0.21
    ]+")
    0.21
     display
    0.21
    deploy
    0.21
    Activations Density 0.003%

    No Known Activations