© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 101876
    Prev
    Next
    INDEX
    Explanations

    water, liquids, and bodies of water

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_16_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
     ይህም
    0.25
     Yad
    0.24
     protrusion
    0.22
     Extend
    0.22
     protrusions
    0.22
     conveying
    0.22
     É
    0.21
     উপলব্ধি
    0.21
    ExprNode
    0.21
     וי
    0.21
    POSITIVE LOGITS
     воды
    0.31
     oceans
    0.31
    海洋
    0.29
    水
    0.28
     wody
    0.26
    水を
    0.26
    water
    0.26
     water
    0.25
     acqua
    0.25
     водой
    0.25
    Activations Density 0.028%

    No Known Activations