© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 87964
    Prev
    Next
    INDEX
    Explanations

    Chinese action verbs

    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_60_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
    Their
    0.48
    They
    0.42
    等的
    0.40
    等
    0.39
    都被
    0.39
    Were
    0.38
    上一
    0.38
     seraient
    0.38
     saranno
    0.38
    DejaVu
    0.37
    POSITIVE LOGITS
     the
    0.64
     has
    0.59
     안
    0.58
     had
    0.55
     have
    0.53
     for
    0.52
     clarity
    0.52
     example
    0.52
     an
    0.50
    安
    0.50
    Activations Density 0.002%

    No Known Activations