© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 29624
    Prev
    Next
    INDEX
    Explanations

    gentleman, bachelor, debonair

    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
     Мор
    0.41
    бір
    0.39
    浦
    0.38
    𝑰
    0.37
    ُم
    0.37
    少女
    0.37
    เทพ
    0.36
    ција
    0.35
    ECUTIVE
    0.35
    ッテ
    0.35
    POSITIVE LOGITS
     rake
    0.64
     libert
    0.59
     gentleman
    0.55
     dand
    0.53
     dissipated
    0.49
    rake
    0.48
     Libert
    0.48
     bachelor
    0.46
    倜
    0.45
     worldly
    0.45
    Activations Density 0.068%

    No Known Activations