© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24460
    Prev
    Next
    INDEX
    Explanations

    silver

    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_56_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
     doing
    1.62
     Doing
    1.55
    Doing
    1.46
    doing
    1.34
     melakukan
    0.95
    做
    0.93
     做
    0.92
     lakukan
    0.84
     doen
    0.81
     делать
    0.79
    POSITIVE LOGITS
     silver
    2.98
    silver
    2.70
    Silver
    2.45
     Silver
    2.39
    银
    2.38
     SILVER
    2.33
    銀
    2.28
     सिल्वर
    1.99
     srebr
    1.98
     silvery
    1.92
    Activations Density 0.064%

    No Known Activations