© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43185
    Prev
    Next
    INDEX
    Explanations

    Crown Jewels

    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_3_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
    
    0.60
    ﻼ
    0.55
    zelfde
    0.54
    0.54
    irittura
    0.53
     decoder
    0.52
    jacking
    0.52
     литера
    0.50
     unimagin
    0.50
     poignant
    0.49
    POSITIVE LOGITS
    ت
    1.09
    0
    0.98
     to
    0.86
    т
    0.84
    س
    0.82
    ты
    0.79
    D
    0.78
    ർ
    0.77
    تس
    0.77
    ש
    0.75
    Activations Density 0.000%

    No Known Activations