© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 5907
    Prev
    Next
    INDEX
    Explanations

    complex numbers like z

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     रियल
    0.49
    Real
    0.43
     real
    0.43
    实
    0.42
     असली
    0.41
    REAL
    0.41
    real
    0.39
     Real
    0.39
     реа
    0.38
     réelle
    0.38
    POSITIVE LOGITS
     z
    0.55
     ז
    0.47
     ز
    0.42
     з
    0.42
    zeta
    0.40
     zás
    0.39
     zaz
    0.38
    z
    0.38
    建設
    0.37
    점으로
    0.37
    Activations Density 0.025%

    No Known Activations