© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3772
    Prev
    Next
    INDEX
    Explanations

    snippets of conversation about software installation and configuration, and also finds french stopwords

    oai_token-act-pair · gemini-2.0-flash

    French

    np_max-act-logits · gemini-2.0-flash

    French

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     خ
    -0.30
     stano
    -0.25
    тра
    -0.24
    т
    -0.24
     фа
    -0.24
    ха
    -0.23
     سپ
    -0.23
     ро
    -0.23
     toal
    -0.23
    в
    -0.22
    POSITIVE LOGITS
     French
    0.97
     Frenchman
    0.93
     franceses
    0.93
     Franse
    0.93
     Ligue
    0.93
     FRENCH
    0.91
     Frenchmen
    0.91
     french
    0.91
     France
    0.89
     francesa
    0.88
    Activations Density 73.799%

    No Known Activations