© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 30238
    Prev
    Next
    INDEX
    Explanations

    count lines (`wc -l`)

    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_40_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
     टोटल
    0.56
    Total
    0.49
     total
    0.48
    totalPages
    0.47
     Total
    0.46
     totale
    0.45
     totaling
    0.45
    总
    0.45
    総
    0.44
     getTotal
    0.43
    POSITIVE LOGITS
     शहरी
    0.42
    present
    0.39
    အစား
    0.39
     কলা
    0.38
     Present
    0.37
    ற்கான
    0.36
    chon
    0.35
     трубо
    0.35
     present
    0.35
    ochemistry
    0.35
    Activations Density 0.001%

    No Known Activations