© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 3071
    Prev
    Next
    INDEX
    Explanations

    racing teams and engineers

    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
    
    0.40
     കമ്പ
    0.39
    𝑃
    0.39
     পি
    0.39
    舀
    0.38
    thres
    0.38
     மிசோ
    0.38
    цева
    0.38
     clothed
    0.38
    ربية
    0.37
    POSITIVE LOGITS
    вр
    0.42
     team
    0.39
     राइड
    0.38
     तळ
    0.37
     Smoking
    0.37
    espół
    0.36
    team
    0.36
     vested
    0.36
     Bahrain
    0.36
    툼
    0.36
    Activations Density 0.006%

    No Known Activations