© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 220337
    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_10_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
    ah
    0.57
     van
    0.56
     de
    0.48
    ach
    0.48
     San
    0.47
     SAR
    0.46
     f
    0.46
    -
    0.46
    on
    0.46
    (
    0.46
    POSITIVE LOGITS
     maximising
    0.58
     домаш
    0.56
     відкри
    0.55
     атмос
    0.50
     customise
    0.50
    tracks
    0.50
     itd
    0.50
    𝘸
    0.49
    𝓾
    0.48
     атаку
    0.48
    Activations Density 0.000%

    No Known Activations