© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 99766
    Prev
    Next
    INDEX
    Explanations

    layout, success, arguments, ET, Daily, Minute

    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_14_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
     ganglion
    0.46
    анг
    0.46
    ッピー
    0.46
     servings
    0.45
    gador
    0.45
    可以
    0.45
     Yokohama
    0.45
    ፨
    0.45
    ;
    0.45
    >
    0.45
    POSITIVE LOGITS
    that
    0.54
    ot
    0.52
     lt
    0.52
    os
    0.50
    ൃത്ത
    0.49
    ressed
    0.49
     സ്ത്രീ
    0.48
    ্যাক
    0.47
    classteacher
    0.47
    itt
    0.47
    Activations Density 0.003%

    No Known Activations