© 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. 12933
    Prev
    Next
    INDEX
    Explanations

    phrases related to soccer/football, mathematics, and battles or rebellions.

    oai_token-act-pair · gemini-2.0-flash

    under

    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
    RSpec
    -0.65
    
    -0.58
    ValueStyle
    -0.56
     ItemStack
    -0.56
    HtmlAttribute
    -0.54
    setViewportView
    -0.54
    ioutil
    -0.52
    makeText
    -0.52
    TagMode
    -0.51
    FormState
    -0.51
    POSITIVE LOGITS
     under
    3.03
    under
    2.59
    Under
    2.48
     Under
    2.38
     UNDER
    2.19
    UNDER
    2.11
     bajo
    1.93
     unter
    1.86
     sotto
    1.70
     sous
    1.69
    Activations Density 4.598%

    No Known Activations