© 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. 11023
    Prev
    Next
    INDEX
    Explanations

    the phrasal verb "come up"

    oai_token-act-pair · gemini-2.0-flash

    come

    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
    webElementXpaths
    -0.78
     come
    -0.77
     came
    -0.77
     coming
    -0.71
     comes
    -0.68
     Coming
    -0.68
    Came
    -0.67
     Came
    -0.67
     Comes
    -0.67
    came
    -0.66
    POSITIVE LOGITS
     up
    2.20
    up
    1.70
     Up
    1.56
    Up
    1.52
     upto
    1.20
     UP
    1.08
    UP
    1.02
    ups
    0.99
    upto
    0.93
    アップ
    0.91
    Activations Density 1.010%

    No Known Activations