© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 195317
    Prev
    Next
    INDEX
    Explanations

    watch or look

    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_46_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
     für
    0.42
    க்காக
    0.42
     mutton
    0.37
     Hilda
    0.37
    ))}
    0.36
     untuk
    0.36
    俊
    0.35
     برای
    0.35
    })}
    0.35
     জন্যও
    0.35
    POSITIVE LOGITS
    istical
    0.42
    izieren
    0.40
    zeniem
    0.40
    istes
    0.39
    UISelectors
    0.39
    Watcher
    0.38
    instell
    0.37
     NVIC
    0.36
     Semi
    0.36
     స్వా
    0.36
    Activations Density 0.001%

    No Known Activations