© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    4. 106423
    Prev
    Next
    INDEX
    Explanations

    divine, divinely, divides, division

    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_1_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
     relaj
    1.03
     conversación
    1.02
    chaft
    0.96
    ன்
    0.95
     preocupación
    0.95
    ς
    0.92
    тэй
    0.91
     cámara
    0.90
     rectángulo
    0.89
    <bos>
    0.87
    POSITIVE LOGITS
    них
    1.16
    َ
    0.97
    ية
    0.95
    ई
    0.94
    ки
    0.93
    ци
    0.93
    ंनी
    0.89
     मदद
    0.89
    ры
    0.89
    ар
    0.89
    Activations Density 0.001%

    No Known Activations