© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 138969
    Prev
    Next
    INDEX
    Explanations

    wound

    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
     wind
    1.38
     winds
    1.31
     wound
    1.25
    風
    1.24
    风
    1.20
     winding
    1.19
     WIND
    1.17
     Wind
    1.16
    Wind
    1.13
    wind
    1.12
    POSITIVE LOGITS
    orig
    0.46
     Care
    0.39
    icano
    0.39
     Sain
    0.38
     orig
    0.38
     clín
    0.37
    𝑵
    0.37
     (_,
    0.35
    embedded
    0.35
     snugly
    0.35
    Activations Density 0.001%

    No Known Activations