© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 260549
    Prev
    Next
    INDEX
    Explanations

    (x, y) coordinates

    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_22_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
     هند
    0.37
    ここ
    0.37
    理論
    0.36
     અહીં
    0.36
     análise
    0.35
    ட்டி
    0.34
    团结
    0.34
    >+</
    0.34
    理论
    0.34
    謦
    0.34
    POSITIVE LOGITS
     filets
    0.43
    mAvailable
    0.42
     afterlife
    0.42
     কমিয়ে
    0.42
     cuz
    0.41
     """)
    0.40
     desay
    0.39
     spikes
    0.38
     जाल
    0.38
    xiety
    0.38
    Activations Density 0.002%

    No Known Activations