© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 233792
    Prev
    Next
    INDEX
    Explanations

    App Store context

    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
     companies
    0.42
    roups
    0.40
     ப
    0.39
    Companies
    0.39
    companies
    0.39
    Wan
    0.39
     बल्
    0.38
     Wan
    0.38
     компаний
    0.38
    ষ্ঠ
    0.38
    POSITIVE LOGITS
    ('/')
    0.41
     parserOptions
    0.41
     publicada
    0.38
     ಉತ್ತರ
    0.37
     reviewer
    0.36
    ხილ
    0.35
     publiée
    0.35
    ='/'
    0.35
    வைப்
    0.35
    بینی
    0.35
    Activations Density 0.003%

    No Known Activations