© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 205119
    Prev
    Next
    INDEX
    Explanations

    drinking water

    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
    Not in Any Lists

    No Comments

    Negative Logits
     water
    1.53
     drinking
    1.39
    Water
    1.37
     Water
    1.34
    水
    1.33
    water
    1.32
     WATER
    1.32
     Drinking
    1.30
    Drinking
    1.29
    drinking
    1.22
    POSITIVE LOGITS
     प्रिया
    0.43
    டக்கலை
    0.38
     গুরুদেব
    0.36
    包人
    0.36
     Pamp
    0.36
    হাট
    0.36
    ">,</
    0.35
    模拟
    0.35
    erny
    0.34
     equivalence
    0.34
    Activations Density 0.011%

    No Known Activations