© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 64084
    Prev
    Next
    INDEX
    Explanations

    committee

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     Cloud
    3.05
     cloud
    2.98
    Cloud
    2.89
    云
    2.72
    雲
    2.63
    cloud
    2.59
     Yun
    2.33
     云
    2.30
     clouds
    2.23
    CLOUD
    2.23
    POSITIVE LOGITS
    Commit
    0.38
     уро
    0.38
    Luther
    0.38
    committee
    0.38
    crate
    0.38
    Committee
    0.38
    Lanc
    0.37
    Lance
    0.37
    obarb
    0.37
     समिती
    0.35
    Activations Density 0.054%

    No Known Activations