© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1536
    Prev
    Next
    INDEX
    Explanations

    scientific research papers with the words "to be" and other associated terms

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    AccessorTable
    -0.55
    OrBuilder
    -0.54
    //
    -0.54
    
    -0.53
    ParallelGroup
    -0.51
    はじめに
    -0.50
    setVerticalGroup
    -0.50
    Przypisy
    -0.49
    XmlAccessType
    -0.48
     GenerationType
    -0.47
    POSITIVE LOGITS
     to
    1.05
    tobe
    0.83
     να
    0.68
    ToBe
    0.67
    Personensuche
    0.64
     lenker
    0.63
     být
    0.61
     essere
    0.61
     être
    0.59
     be
    0.58
    Activations Density 2.015%

    No Known Activations