© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 113475
    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_2_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
    dalam
    0.89
    tp
    0.86
    ر
    0.85
    ls
    0.83
    lh
    0.82
    ాలు
    0.81
    to
    0.80
    트
    0.80
    datos
    0.80
    ርሃ
    0.80
    POSITIVE LOGITS
    am
    1.45
     on
    1.15
    :
    1.07
    ig
    1.02
     trabalh
    0.96
    ie
    0.90
    ()
    0.86
    hesized
    0.86
    1
    0.86
    et
    0.85
    Activations Density 0.000%

    No Known Activations