© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 154417
    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_50_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
    Ga
    0.52
     Ga
    0.47
     ga
    0.45
     Gao
    0.44
     targ
    0.43
    IQ
    0.41
    zend
    0.40
    yam
    0.40
     ط
    0.39
    禅
    0.38
    POSITIVE LOGITS
     J
    0.56
    J
    0.52
     ज
    0.50
     Jio
    0.49
    𝐽
    0.49
     j
    0.46
     জ
    0.45
     Дж
    0.43
     జి
    0.42
     ج
    0.41
    Activations Density 0.000%

    No Known Activations