© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 129979
    Prev
    Next
    INDEX
    Explanations

    closing code blocks

    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_25_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
     Flav
    0.40
     Fl
    0.39
     Princess
    0.36
     coherent
    0.35
     Restaurant
    0.35
     кро
    0.35
     w
    0.34
     CO
    0.34
     Poll
    0.34
     Blue
    0.33
    POSITIVE LOGITS
    :”
    0.42
    疽
    0.42
    ন্ত্র
    0.42
     evangel
    0.41
    neyland
    0.41
    
    0.41
    udsman
    0.40
    myapplication
    0.40
    或者
    0.40
    drž
    0.39
    Activations Density 0.000%

    No Known Activations