© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5876
    Prev
    Next
    INDEX
    Explanations

    ruminating or rummy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    𝘨
    2.98
     belakang
    2.87
    𝘮
    2.82
    environ
    2.75
    𝘺
    2.70
    да
    2.70
    𝘱
    2.70
    wght
    2.69
    𝘧
    2.69
    𝘥
    2.62
    POSITIVE LOGITS
    াচার
    2.64
    ून
    2.63
     '?
    2.51
     всей
    2.50
     IndexPath
    2.47
    ພ
    2.35
    ጀመሪያ
    2.33
    HOW
    2.30
    ور
    2.29
     गोपाल
    2.29
    Activations Density 0.003%

    No Known Activations