© 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-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 211994
    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
    Negative Logits
     rising
    0.47
    ivel
    0.46
     emerging
    0.46
    any
    0.45
     gambling
    0.45
    9
    0.45
     y
    0.45
    force
    0.44
     fierce
    0.44
     Dancing
    0.43
    POSITIVE LOGITS
    𒀕
    0.52
     যাঁ
    0.50
    朊
    0.49
     ಹೆಸ
    0.48
    綀
    0.48
    鵬
    0.47
    裵
    0.47
    Routine
    0.46
    Დ
    0.46
    正確
    0.46
    Activations Density 0.000%

    No Known Activations