© 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. 200465
    Prev
    Next
    INDEX
    Explanations

    Chinese

    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
    子
    2.70
    子的
    2.44
    子が
    2.11
    子の
    2.09
    子は
    2.03
    子上
    1.97
     子
    1.88
     child
    1.83
     tử
    1.78
    ⼦
    1.74
    POSITIVE LOGITS
     Насе
    0.40
    ermost
    0.40
    enderita
    0.39
    чва
    0.37
     পর্যবে
    0.37
    Males
    0.37
    rief
    0.37
    aiset
    0.36
    ημ
    0.36
    ᶤ
    0.36
    Activations Density 0.013%

    No Known Activations