© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9828
    Prev
    Next
    INDEX
    Explanations

    action verbs that describe laying out a plan or design, as well as related words like "chart," "axes," and "layout," and it faintly recognizes words with moral connotations like "good" and "fair."

    oai_token-act-pair · gemini-2.0-flash

    laid

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     lay
    -2.83
     Lay
    -2.39
    Lay
    -2.36
     LAY
    -2.16
     laying
    -2.11
     lays
    -2.02
    lay
    -1.93
     Layout
    -1.91
     laid
    -1.89
     layout
    -1.82
    POSITIVE LOGITS
    
    0.64
    rmtree
    0.50
    :+:
    0.50
     OnTrigger
    0.47
     NSCoder
    0.47
    localVar
    0.47
    Hentet
    0.47
     confronti
    0.46
    Autoritní
    0.45
    closePath
    0.44
    Activations Density 1.632%

    No Known Activations