© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 23-GEMMASCOPE-TRANSCODER-16K
    4. 10882
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with internet articles, blogs, and search engine optimization

    oai_token-act-pair · gemini-2.0-flash

    blog posts and articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    ́
    -0.34
    ­
    -0.29
    <unused63>
    -0.29
    (_
    -0.28
    <u>
    -0.28
    ´
    -0.28
    �
    -0.28
    ó
    -0.28
    ni
    -0.27
    <b>
    -0.27
    POSITIVE LOGITS
    GEBURTSDATUM
    1.42
     للاسماء
    1.30
    featureID
    1.28
     ویکی‌پدیا
    1.23
    AddTagHelper
    1.20
     Roskov
    1.20
    MigrationBuilder
    1.20
     ویکی‌پدی
    1.19
     CreateTagHelper
    1.18
    تقاوى
    1.17
    Activations Density 15.693%

    No Known Activations