© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257106
    Prev
    Next
    INDEX
    Explanations

    muscle mass

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_22_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
    ()*
    0.34
    USTOM
    0.31
    hts
    0.30
     prehr
    0.29
     እስ
    0.29
    ́u
    0.28
    ilen
    0.28
     പിന്തു
    0.28
     ينا
    0.28
    唕
    0.28
    POSITIVE LOGITS
    вета
    0.32
    Reconnect
    0.32
     renewing
    0.32
     भला
    0.31
     sure
    0.31
    тических
    0.31
     well
    0.30
     seemed
    0.30
    Méd
    0.29
    ခြ
    0.29
    Activations Density 0.006%

    No Known Activations