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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9541
    Prev
    Next
    INDEX
    Explanations

    C code block delimiters, keywords "const", and the combination "BU"

    oai_token-act-pair · gemini-2.0-flash

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    bootstrapcdn
    -0.93
     ſeveral
    -0.83
     iſt
    -0.81
     Reſ
    -0.79
     Conſ
    -0.79
     Eſ
    -0.78
    wiſe
    -0.77
     BoxFit
    -0.76
     Inſ
    -0.75
     Beſ
    -0.73
    POSITIVE LOGITS
    <bos>
    0.84
     
    0.62
    '
    0.54
    ’
    0.48
      
    0.47
     in
    0.47
    ,
    0.45
     The
    0.45
    I
    0.45
    -
    0.43
    Activations Density 1.092%

    No Known Activations