© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 177841
    Prev
    Next
    INDEX
    Explanations

    utility

    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_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MS
    0.41
     imbalance
    0.40
     कूल
    0.38
    ம்ச
    0.38
    芒
    0.38
    Ra
    0.38
    闷
    0.38
     imbalances
    0.37
     ஊற
    0.37
     rollup
    0.37
    POSITIVE LOGITS
     Utility
    0.51
     utility
    0.50
    utility
    0.49
    Utility
    0.47
     A
    0.45
     Aga
    0.45
     AK
    0.38
    aggregation
    0.37
     Chis
    0.37
     यु
    0.37
    Activations Density 0.005%

    No Known Activations