© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 83692
    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_23_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
     FLASH
    0.38
    Used
    0.36
     parcel
    0.35
     хотела
    0.35
    ፧
    0.35
     colonel
    0.35
    므로
    0.34
    ZM
    0.34
    zta
    0.34
    abets
    0.34
    POSITIVE LOGITS
    utte
    0.38
    conn
    0.36
     conn
    0.36
     irland
    0.36
    டித்த
    0.35
     subterr
    0.35
    cons
    0.34
     ఈ
    0.34
     प्रदूषण
    0.34
    शियल
    0.34
    Activations Density 0.000%

    No Known Activations