© 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. 114
    Prev
    Next
    INDEX
    Explanations

    references to American sports teams

    oai_token-act-pair · gemini-2.0-flash

    Sports teams and cities

    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
    expandindo
    -0.77
    WriteBarrier
    -0.76
    出版年
    -0.74
    دانشنامهٔ
    -0.65
    WebElementEntity
    -0.63
     betweenstory
    -0.63
    jsxFileName
    -0.63
     EconPapers
    -0.63
     jsPsych
    -0.62
    elemField
    -0.62
    POSITIVE LOGITS
    /*
    0.47
     Züge
    0.44
     withal
    0.44
     Bakers
    0.44
     AppCompatTheme
    0.43
     swimmers
    0.43
    dibles
    0.43
     ladders
    0.43
     Farmers
    0.42
     scolas
    0.42
    Activations Density 2.335%

    No Known Activations