© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    4. 51538
    Prev
    Next
    INDEX
    Explanations

    mathematical sets and structures

    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_30_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
     twins
    0.37
     mutually
    0.35
     cristianos
    0.34
     быть
    0.33
    YX
    0.33
    ([],
    0.33
    깝
    0.33
     sistema
    0.33
     систему
    0.33
    =")"
    0.32
    POSITIVE LOGITS
     நாளில்
    0.38
    reversible
    0.37
    advisor
    0.37
     объяс
    0.37
     Hohen
    0.36
    asambhavam
    0.36
    Marco
    0.36
     예상
    0.36
    ML
    0.36
    him
    0.36
    Activations Density 0.004%

    No Known Activations