© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 200450
    Prev
    Next
    INDEX
    Explanations

    family relation

    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
     가정
    0.42
    rapy
    0.37
    ulagway
    0.36
    descriptor
    0.35
     Precipitation
    0.35
    upra
    0.35
    =",
    0.34
    峠
    0.34
     PC
    0.34
    :@
    0.34
    POSITIVE LOGITS
    亲
    2.06
    親
    2.02
     친
    1.87
     親
    1.61
     род
    1.52
    친
    1.51
     родствен
    1.20
     parent
    1.19
    parent
    1.18
     paren
    1.14
    Activations Density 0.002%

    No Known Activations