© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 66728
    Prev
    Next
    INDEX
    Explanations

    Korean clothing terms

    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_51_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
     건
    0.54
    건
    0.47
     build
    0.45
    gaia
    0.44
     га
    0.44
    ガ
    0.42
     arsine
    0.42
     kiến
    0.42
    <0x8D>
    0.41
     gaz
    0.40
    POSITIVE LOGITS
    풀
    0.60
     풀
    0.58
     Fuller
    0.49
     풀어
    0.47
    Pull
    0.47
     SA
    0.47
     FULLER
    0.46
     Sa
    0.45
     Saddam
    0.44
    Sa
    0.44
    Activations Density 0.004%

    No Known Activations