© 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-3-4B-IT
    3. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 9390
    Prev
    Next
    INDEX
    Explanations

    javascript code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
    ေါ
    0.65
     Preferred
    0.62
     पुण्य
    0.62
    ∑</
    0.61
     منتقل
    0.60
    өм
    0.60
     Document
    0.60
    文本
    0.60
     खुला
    0.59
    iança
    0.59
    POSITIVE LOGITS
     restrictions
    0.64
    રાજ
    0.62
     обре
    0.62
     oby
    0.62
     टेली
    0.61
     reactionary
    0.59
     reflexive
    0.59
     duties
    0.59
    隴
    0.58
     gloomy
    0.57
    Activations Density 0.005%

    No Known Activations