© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10691
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to pausing an activity or a break during a trip or game

    oai_token-act-pair · gemini-2.0-flash

    to/for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     surla
    -0.99
    IntoConstraints
    -0.94
    GEBURTSDATUM
    -0.85
    InvalidProtocol
    -0.79
    
    -0.78
    Revenir
    -0.77
    HideFlags
    -0.73
     ModelExpression
    -0.73
    ValueStyle
    -0.72
    MemoryWarning
    -0.71
    POSITIVE LOGITS
    InsertCommand
    0.43
    Frequent
    0.41
    ause
    0.41
    weil
    0.39
    前の
    0.38
     discuss
    0.37
     to
    0.37
    тельству
    0.37
    venirs
    0.36
     roble
    0.35
    Activations Density 1.386%

    No Known Activations