© 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. 28321
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    გან
    0.43
     LIKE
    0.43
     sienten
    0.41
     것처럼
    0.39
     beğen
    0.38
    辰
    0.38
     like
    0.38
    LIKE
    0.38
     merasa
    0.37
     Like
    0.36
    POSITIVE LOGITS
     more
    1.10
     أكثر
    0.95
    more
    0.92
     اكثر
    0.86
     lebih
    0.86
     більше
    0.84
    มากกว่า
    0.84
     más
    0.84
     अधिक
    0.80
     더
    0.77
    Activations Density 0.000%

    No Known Activations