© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 158005
    Prev
    Next
    INDEX
    Explanations

    amy/omy

    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
    מן
    0.43
     Mariano
    0.41
     dispositivo
    0.39
     MMS
    0.38
    ื่น
    0.38
     Muk
    0.38
     Viva
    0.38
    ࿐
    0.38
     LO
    0.37
    lings
    0.36
    POSITIVE LOGITS
    amy
    0.59
    Amy
    0.54
     letting
    0.45
     amy
    0.45
    umy
    0.44
    omy
    0.43
    usher
    0.42
    omyc
    0.41
    ামী
    0.41
    aphyl
    0.41
    Activations Density 0.000%

    No Known Activations