© 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
    2. Gemma-3-27B-IT
    3. 46-GEMMASCOPE-2-TRANSCODER-262K
    4. 198366
    Prev
    Next
    INDEX
    Explanations

    personal appearance, grooming

    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_46_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
     combing
    1.24
    梳
    1.17
     combs
    1.15
     comb
    1.13
     combed
    1.10
     hairstyle
    1.07
     pente
    1.06
     hairstyles
    1.00
     haird
    1.00
     Hairst
    0.93
    POSITIVE LOGITS
    ZM
    0.38
    Tx
    0.38
     চন্দ্র
    0.37
    逘
    0.37
     অনলাইন
    0.37
     ZONE
    0.37
     DBI
    0.35
     میرا
    0.35
     enquire
    0.34
     مخ
    0.34
    Activations Density 0.003%

    No Known Activations