© 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. 155201
    Prev
    Next
    INDEX
    Explanations

    Jade, Chad

    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
    蹑
    0.48
     NN
    0.47
    NEE
    0.47
     NE
    0.43
    磯
    0.41
     NX
    0.40
    NQ
    0.40
     네
    0.39
     ネ
    0.39
    cision
    0.38
    POSITIVE LOGITS
    جد
    0.83
     جد
    0.78
    Jade
    0.76
     Jade
    0.75
     jad
    0.75
     yen
    0.72
     Jad
    0.72
     chad
    0.70
     Yen
    0.70
     jade
    0.68
    Activations Density 0.000%

    No Known Activations