© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-TRANSCODER-262K
    4. 100274
    Prev
    Next
    INDEX
    Explanations

    lime, there, fair question

    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_16_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
    computed
    0.51
    م
    0.51
    integrity
    0.50
    arcs
    0.49
    processing
    0.48
    oqu
    0.48
    industrial
    0.48
    帶
    0.48
    subjects
    0.46
    нений
    0.45
    POSITIVE LOGITS
     Charity
    0.54
     Charitable
    0.53
     Goods
    0.52
     Avocado
    0.52
     Picnic
    0.51
     زمین
    0.50
     Broccoli
    0.50
     Half
    0.48
     Crop
    0.48
     Manual
    0.47
    Activations Density 0.000%

    No Known Activations