© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45381
    Prev
    Next
    INDEX
    Explanations

    BASIC programs and PET Sinclair

    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_13_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
    陘
    0.33
     времени
    0.32
    ಿನಲ್ಲಿ
    0.32
     vremena
    0.31
     ameryka
    0.31
     clinics
    0.30
     lemons
    0.29
     치료
    0.29
    চিক
    0.29
    梟
    0.29
    POSITIVE LOGITS
     ज
    0.33
    etail
    0.30
     कांच
    0.29
     டை
    0.29
    knife
    0.29
    et
    0.29
     Waals
    0.28
     монта
    0.28
    ioutil
    0.27
    繁殖
    0.27
    Activations Density 0.013%

    No Known Activations