© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 74483
    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_31_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
     სი
    0.38
    sev
    0.38
    contains
    0.38
    heni
    0.37
     nest
    0.36
    詠
    0.36
     abrigo
    0.35
     treas
    0.35
    mgmt
    0.34
     heure
    0.34
    POSITIVE LOGITS
    ển
    0.42
    ărilor
    0.38
    Bibliography
    0.37
     IF
    0.37
     абсолю
    0.36
    换
    0.36
     फैंस
    0.36
     মোল
    0.36
     уеннары
    0.35
    Inserted
    0.35
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.