© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174755
    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_20_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
    া
    0.55
    Precio
    0.51
    Settl
    0.51
     fís
    0.50
    Eli
    0.50
    Furniture
    0.50
     Sı
    0.48
    anedi
    0.47
    াভাব
    0.46
    s
    0.46
    POSITIVE LOGITS
     preventing
    0.53
     ஏற்றுக்கொள்ள
    0.48
     নিষ্ঠ
    0.46
     ар
    0.46
    ਫ਼
    0.45
    わかり
    0.44
     misconception
    0.44
     அவற்றை
    0.44
     அவற்ற
    0.44
    enamefont
    0.43
    Activations Density 0.000%

    No Known Activations