© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13939
    Prev
    Next
    INDEX
    Explanations

    words that function as conjunctions, helping to tie together the overall narrative

    oai_token-act-pair · gemini-2.0-flash

    structure/order

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    Revenir
    -0.60
    CloseOperation
    -0.59
     CommonModule
    -0.57
     Pública
    -0.55
     Garrick
    -0.54
     viewDidLoad
    -0.54
     <",
    -0.54
    iket
    -0.54
     <<-
    -0.52
    coroutines
    -0.52
    POSITIVE LOGITS
     order
    0.90
     structure
    0.86
    structure
    0.76
     purpose
    0.73
    purpose
    0.68
     variety
    0.68
     beginnetje
    0.67
     Structure
    0.66
     meaning
    0.66
    order
    0.63
    Activations Density 3.423%

    No Known Activations