© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 84656
    Prev
    Next
    INDEX
    Explanations

    database table prefix

    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_23_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
    ારા
    0.45
     хло
    0.43
    CommandLine
    0.43
     класса
    0.42
     ג
    0.41
    ныя
    0.40
     факторы
    0.40
     кат
    0.39
     ра
    0.39
    回の
    0.39
    POSITIVE LOGITS
    server
    0.42
     مدیریت
    0.41
    encing
    0.40
    wider
    0.40
     ፣
    0.40
    hearts
    0.39
    ောက်ပ
    0.39
    </em>
    0.39
    dr
    0.38
    dj
    0.38
    Activations Density 0.001%

    No Known Activations