© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6767
    Prev
    Next
    INDEX
    Explanations

    words related to groups of people and formal situations

    oai_token-act-pair · gemini-2.0-flash

    Assembling

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    HasForeignKey
    -0.64
    ISupport
    -0.63
     snippetHide
    -0.60
    NameInMap
    -0.57
    VIAF
    -0.57
    webElementGuid
    -0.57
    fillType
    -0.55
    RegressionTest
    -0.55
     MainAxisSize
    -0.54
    WriteAttribute
    -0.54
    POSITIVE LOGITS
     assemble
    1.04
     gathering
    0.96
     gather
    0.92
     assembly
    0.91
     assembled
    0.90
     Assemble
    0.90
     assembling
    0.90
     assemb
    0.87
     gathered
    0.87
    assemble
    0.85
    Activations Density 0.715%

    No Known Activations