© 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. 13589
    Prev
    Next
    INDEX
    Explanations

    scientific experimental text with numerical measurements of time or amounts, and statistical significance

    oai_token-act-pair · gemini-2.0-flash

    Duration of scientific experiments

    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
    ViewFeatures
    -0.55
    PerformLayout
    -0.52
    UrlResolution
    -0.51
    Javadoc
    -0.40
    Geografía
    -0.40
     tarto
    -0.39
     su
    -0.37
     
    -0.37
     van
    -0.36
     en
    -0.36
    POSITIVE LOGITS
     myſelf
    0.82
     Monfieur
    0.81
     itſelf
    0.79
    ſelf
    0.79
     ་་
    0.77
     ―――――
    0.76
    ^(@)
    0.76
    ſelves
    0.75
     Theſe
    0.73
     iſt
    0.71
    Activations Density 11.638%

    No Known Activations