© 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. 156852
    Prev
    Next
    INDEX
    Explanations

    food and drinks

    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
    Water
    1.98
     water
    1.93
     Water
    1.92
    水
    1.88
    water
    1.83
     WATER
    1.78
    WATER
    1.73
     nước
    1.70
     Wasser
    1.56
     वाटर
    1.54
    POSITIVE LOGITS
     Kusum
    0.39
    Cass
    0.38
    rite
    0.37
    cass
    0.36
     Cato
    0.36
    窸
    0.35
     Polk
    0.35
    agram
    0.34
     tann
    0.34
     Cromwell
    0.34
    Activations Density 0.010%

    No Known Activations