© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13262
    Prev
    Next
    INDEX
    Explanations

    breaching, surfacing, swimming upstream

    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
     legs
    0.50
    legs
    0.45
     Legs
    0.43
    
    0.43
    ขา
    0.42
    тку
    0.42
    腳
    0.40
    )&&
    0.39
    անակ
    0.39
    orage
    0.38
    POSITIVE LOGITS
     tail
    0.59
    surface
    0.58
     breaching
    0.57
     surface
    0.56
     breach
    0.55
     Surface
    0.55
     surfacing
    0.55
    tail
    0.54
     breaches
    0.54
     breached
    0.54
    Activations Density 0.062%

    No Known Activations