© 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. 205001
    Prev
    Next
    INDEX
    Explanations

    z character variants

    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
    投
    0.66
    热
    0.65
    熱
    0.61
     drills
    0.57
     drill
    0.52
     热
    0.51
     hot
    0.50
     hotter
    0.50
     ड्रिल
    0.49
    hot
    0.49
    POSITIVE LOGITS
     z
    2.61
     ز
    2.13
     з
    2.02
     Z
    1.84
     З
    1.52
     ז
    1.48
    Z
    1.47
    z
    1.35
    ｚ
    1.18
    𝑧
    1.18
    Activations Density 0.001%

    No Known Activations