© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8956
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
    nst
    0.87
    care
    0.77
    Yours
    0.76
     sealed
    0.75
    突出
    0.74
    n
    0.73
    ීය
    0.71
    
    0.70
    monospace
    0.70
    nie
    0.67
    POSITIVE LOGITS
    м
    0.94
     partir
    0.91
    此之外
    0.88
     Един
    0.86
     veces
    0.84
     homozyg
    0.82
     finales
    0.80
     complètement
    0.80
     egos
    0.80
    র্ষণ
    0.78
    Activations Density 0.008%

    No Known Activations