© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6271
    Prev
    Next
    INDEX
    Explanations

    the word "instrument"

    oai_token-act-pair · gemini-2.0-flash

    instrument

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     soeur
    -0.91
    ⓧ
    -0.89
     barbati
    -0.83
    mybatisplus
    -0.81
     chré
    -0.80
     figliu
    -0.80
    migrationBuilder
    -0.79
     متعلقه
    -0.79
     enfans
    -0.79
     feroit
    -0.78
    POSITIVE LOGITS
     the
    1.02
     
    1.00
    <bos>
    1.00
     The
    0.74
     well
    0.73
     I
    0.71
     In
    0.69
    ↵
    0.68
     '
    0.67
     local
    0.66
    Activations Density 0.663%

    No Known Activations