© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 219616
    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_47_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
    aby
    0.38
    级别
    0.38
    pre
    0.37
    ivities
    0.37
     chains
    0.37
    这个时候
    0.37
    acy
    0.36
     blogger
    0.36
    聰
    0.35
    OSH
    0.35
    POSITIVE LOGITS
     Jacobi
    0.41
    Jacobi
    0.40
    🚛
    0.40
    envs
    0.40
     TeV
    0.39
    Jak
    0.39
    джа
    0.39
    Putting
    0.38
    devtools
    0.38
    El
    0.38
    Activations Density 0.000%

    No Known Activations