© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 77031
    Prev
    Next
    INDEX
    Explanations

    c++ includes

    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_31_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
     contaminants
    0.39
     inequities
    0.39
     asymmetries
    0.38
    ране
    0.37
     permeates
    0.37
     parasites
    0.36
    ரும்பு
    0.36
    ^{-(
    0.35
    区块链
    0.35
     inhomogeneity
    0.35
    POSITIVE LOGITS
    瞌
    0.40
    ToolStrip
    0.38
    antu
    0.38
    幻想
    0.38
    MemoryWarning
    0.37
    ဆို
    0.36
     winged
    0.35
     पोर्टल
    0.35
    想象
    0.35
    Framework
    0.34
    Activations Density 0.000%

    No Known Activations