© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1598
    Prev
    Next
    INDEX
    Explanations

    text related to books and creative work by artists, especially children's books that tell a story

    oai_token-act-pair · gemini-2.0-flash

    books

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    <bos>
    -0.48
     suivant
    -0.47
     udara
    -0.42
     blanches
    -0.40
     vòng
    -0.40
     heti
    -0.40
     hesap
    -0.40
     encontraban
    -0.40
    ุทธ
    -0.40
     kolom
    -0.40
    POSITIVE LOGITS
     SwitchCompat
    0.77
    ьаж
    0.73
     صوتيه
    0.73
    createCanvas
    0.69
     nahilalakip
    0.68
    ChildScrollView
    0.65
    ()]);
    0.64
    theless
    0.64
    URLConnection
    0.62
    出版年
    0.61
    Activations Density 0.326%

    No Known Activations