© 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. 11124
    Prev
    Next
    INDEX
    Explanations

    words and phrases that connect clauses and ideas in a discussion or argument

    oai_token-act-pair · 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
     vectorielle
    -0.57
    ☆☆☆☆
    -0.55
    Groetjes
    -0.52
    posables
    -0.50
     réflexion
    -0.50
    WriteLiteral
    -0.50
     soñ
    -0.50
    portál
    -0.49
    ↘
    -0.49
     cornstarch
    -0.49
    POSITIVE LOGITS
    expandindo
    0.75
     snippetHide
    0.72
    XmlAccessorType
    0.69
    曖昧さ回避
    0.64
    HasAnnotation
    0.59
    adaptiveStyles
    0.58
     lenker
    0.54
    prim
    0.54
    findpost
    0.54
    gameserver
    0.54
    Activations Density 1.359%

    No Known Activations