© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12489
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and programming code

    oai_token-act-pair · gemini-2.0-flash

    code/mathematical notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    Demografía
    -0.56
    ellees
    -0.55
     hậu
    -0.53
    Referensi
    -0.53
    jednoc
    -0.53
    enschutzer
    -0.50
    hasMoreElements
    -0.49
    ParallelGroup
    -0.49
    доне
    -0.48
     Breen
    -0.48
    POSITIVE LOGITS
    LLocation
    0.66
     AssemblyTitle
    0.65
    addGap
    0.61
     يتيمه
    0.59
    <bos>
    0.57
    BeginInit
    0.57
    Gambas
    0.56
    '])){
    0.56
     UA
    0.55
     Whigs
    0.55
    Activations Density 2.782%

    No Known Activations