© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11396
    Prev
    Next
    INDEX
    Explanations

    the phrase "to come" or similar phrases indicating the future

    oai_token-act-pair · gemini-2.0-flash

    say "come" and "comes"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     AssemblyProduct
    -0.71
     Wikimedijinoj
    -0.62
    findpost
    -0.61
     propOrder
    -0.56
    angliski
    -0.54
    PDOException
    -0.53
    kháu
    -0.52
    verwijspagina
    -0.52
     ruinas
    -0.52
    PerformLayout
    -0.51
    POSITIVE LOGITS
     comes
    2.83
     come
    2.69
    comes
    2.45
     Comes
    2.36
     COMES
    2.33
     came
    2.28
    come
    2.23
     Come
    2.20
     COME
    2.20
    Come
    2.16
    Activations Density 2.100%

    No Known Activations