© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15281
    Prev
    Next
    INDEX
    Explanations

    parts of code related to Lists, queues or other ordered collections

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     added
    -2.22
     add
    -1.96
     adding
    -1.95
    added
    -1.89
     addition
    -1.84
     Added
    -1.84
     adds
    -1.82
    Added
    -1.76
     Adding
    -1.75
    Adding
    -1.73
    POSITIVE LOGITS
    
    0.73
     estekak
    0.70
    脚注の使い方
    0.66
    usermodel
    0.65
    ThroughAttribute
    0.62
    IntoConstraints
    0.61
     Normdatei
    0.60
     Wikiseite
    0.59
    🧵
    0.59
    }{#
    0.59
    Activations Density 0.639%

    No Known Activations