© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 243195
    Prev
    Next
    INDEX
    Explanations

    RxJava, RxJS, computer

    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
    Song
    0.41
     Song
    0.40
     piccoli
    0.39
     убий
    0.39
     Brawl
    0.39
    ブレー
    0.38
     imaginations
    0.38
    寯
    0.38
     SALE
    0.38
    呫
    0.38
    POSITIVE LOGITS
    计算机
    0.41
    コンピュータ
    0.39
    laser
    0.39
    adera
    0.39
     компьютер
    0.38
    コンピュー
    0.37
    etur
    0.36
    encrypt
    0.36
     Faithful
    0.35
     Computer
    0.35
    Activations Density 0.000%

    No Known Activations