© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21767
    Prev
    Next
    INDEX
    Explanations

    esp

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    喍
    0.38
     Volleyball
    0.37
     Surfaces
    0.37
    AZIONE
    0.36
     образовањем
    0.34
    ப்பர்
    0.34
    yfik
    0.33
     SP
    0.33
     verbunden
    0.33
     OFFICES
    0.33
    POSITIVE LOGITS
    ｐ
    0.51
    ൂടെ
    0.42
    প
    0.42
    ionic
    0.38
    ێنی
    0.38
    stock
    0.36
    landish
    0.36
     それぞれ
    0.36
     గ్రహ
    0.36
    香港
    0.35
    Activations Density 0.000%

    No Known Activations