© 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. 911
    Prev
    Next
    INDEX
    Explanations

    words associated with future launches of apps or tech products as well as words indicating possible but uncertain things

    oai_token-act-pair · gemini-2.0-flash

    upcoming events

    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
    Демографія
    -0.73
    PDOException
    -0.66
     disambiguazione
    -0.64
    !("{}",
    -0.62
    PerformLayout
    -0.61
    цездатний
    -0.61
    EndInit
    -0.60
     Numerade
    -0.60
    DeleteBehavior
    -0.59
    atisk
    -0.59
    POSITIVE LOGITS
     coming
    2.66
     Coming
    2.30
    coming
    2.25
    Coming
    2.23
     COMING
    2.03
     upcoming
    1.71
    COMING
    1.70
     comming
    1.64
     approaching
    1.53
     comin
    1.53
    Activations Density 1.028%

    No Known Activations