© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45278
    Prev
    Next
    INDEX
    Explanations

    unicode punctuation

    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_13_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
    NodeType
    0.57
    También
    0.54
    Expenses
    0.50
    ޟ
    0.50
     asimismo
    0.50
    Util
    0.50
    Tamb
    0.49
    amus
    0.49
     casually
    0.48
    Amit
    0.48
    POSITIVE LOGITS
    il
    0.59
    న్
    0.58
    ว
    0.58
    ล
    0.58
    ้
    0.57
     warmer
    0.56
    ла
    0.55
     Mandalorian
    0.55
    at
    0.55
     गौरी
    0.54
    Activations Density 0.003%

    No Known Activations