© 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-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 9703
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating excitement or positive reviews in descriptive writing, particularly for creative works such as books, movies, or music.

    oai_token-act-pair · gemini-2.0-flash

    Release order

    np_max-act-logits · gemini-2.0-flash
    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
     Anſ
    -0.60
     Theſe
    -0.59
    berdayakan
    -0.58
    tagHelper
    -0.57
    VIRONMENT
    -0.57
     &'
    -0.56
     classics
    -0.56
     Efq
    -0.55
    existsSync
    -0.54
    養
    -0.54
    POSITIVE LOGITS
    tvguidetime
    0.57
     незавершена
    0.54
     ModelRenderer
    0.46
    ViewFeatures
    0.45
     release
    0.45
    Filmografie
    0.45
     بتاريخ
    0.43
    ьажоргаш
    0.42
    ));
    
    0.40
     ویکی‌پدیای
    0.40
    Activations Density 1.856%

    No Known Activations