© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4085
    Prev
    Next
    INDEX
    Explanations

    instances of pausing an activity or event

    oai_token-act-pair · gemini-2.0-flash

    deferred

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     suspended
    -1.04
     suspension
    -0.89
     pause
    -0.82
     paused
    -0.81
     suspend
    -0.80
    suspended
    -0.77
     defer
    -0.75
    pause
    -0.75
    suspension
    -0.75
     deferred
    -0.74
    POSITIVE LOGITS
    ValueStyle
    0.80
    requestCode
    0.70
     continúas
    0.66
     Monfieur
    0.61
     converti
    0.59
     auroit
    0.59
     auffi
    0.58
     Meksi
    0.57
     algod
    0.57
     Longman
    0.56
    Activations Density 1.395%

    No Known Activations