© 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-3-4B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9526
    Prev
    Next
    INDEX
    Explanations

    rubbing friction

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
     troisième
    0.96
     ketiga
    0.93
     ثالث
    0.88
    ۳
    0.84
     ৩
    0.81
    ٣
    0.76
     سوم
    0.76
     üçüncü
    0.76
     trzec
    0.74
     thirds
    0.73
    POSITIVE LOGITS
     rubbing
    0.98
     scraping
    0.95
     rub
    0.95
    剐
    0.84
     scrape
    0.82
     scrapes
    0.78
     Rub
    0.77
     chaf
    0.74
     heat
    0.72
     snag
    0.72
    Activations Density 0.278%

    No Known Activations