© 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. 13625
    Prev
    Next
    INDEX
    Explanations

    mentions of waiting in line, or standing in a line

    oai_token-act-pair · gemini-2.0-flash

    waiting

    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
     waiting
    -3.16
     Waiting
    -2.98
     wait
    -2.95
     waited
    -2.77
    waiting
    -2.73
     waits
    -2.70
    Waiting
    -2.70
     Wait
    -2.63
    wait
    -2.59
    Wait
    -2.50
    POSITIVE LOGITS
    wied
    0.49
    鰭
    0.48
     насељу
    0.46
    erda
    0.44
    oprecipitation
    0.43
    bourhood
    0.43
    ditor
    0.42
    nessy
    0.41
    нциклопе
    0.41
    toggleClass
    0.41
    Activations Density 1.816%

    No Known Activations