© 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. 24159
    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
    findings
    0.49
    兩
    0.47
    story
    0.45
    verifier
    0.45
    remaining
    0.43
    辨
    0.43
    几
    0.42
    تبقى
    0.41
    两
    0.41
    scores
    0.41
    POSITIVE LOGITS
     día
    0.63
     suffoc
    0.61
     کار
    0.60
     प्यार
    0.59
     городе
    0.59
     educación
    0.56
     économique
    0.54
     этапе
    0.54
     otoño
    0.54
     नियंत्रण
    0.54
    Activations Density 0.000%

    No Known Activations