© 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
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2656
    Prev
    Next
    INDEX
    Explanations

    the word "daily," and sometimes words near it, in a variety of contexts

    oai_token-act-pair · gemini-2.0-flash

    daily

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     Bur
    -0.45
     com
    -0.41
    bör
    -0.40
    Hentet
    -0.40
    <eos>
    -0.39
     thérape
    -0.39
    XtraGrid
    -0.39
     ker
    -0.39
     εν
    -0.39
     próprias
    -0.38
    POSITIVE LOGITS
     betweenstory
    0.87
     annually
    0.80
    Aholisi
    0.79
     regularly
    0.76
     Италијани
    0.72
    XmlAccessorType
    0.72
     yearly
    0.72
     zirc
    0.70
    MigrationBuilder
    0.70
    每年
    0.69
    Activations Density 0.170%

    No Known Activations