© 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-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6175
    Prev
    Next
    INDEX
    Explanations

    Japanese words/phrases related to programming and debugging

    oai_token-act-pair · gemini-2.0-flash

    めて

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ませんか
    -0.85
    しまいます
    -0.82
    <bos>
    -0.80
    おります
    -0.75
    ますが
    -0.70
     Efq
    -0.70
    いかがでしょうか
    -0.70
    行きます
    -0.69
    しまいました
    -0.69
     pleaſure
    -0.69
    POSITIVE LOGITS
    expandindo
    0.89
    +:+
    0.88
    RectangleBorder
    0.82
    发表于
    0.76
    googleapis
    0.71
    mybatisplus
    0.71
     NSCoder
    0.70
    bootstrapcdn
    0.70
    겨
    0.68
    ็จ
    0.68
    Activations Density 1.587%

    No Known Activations