© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2933
    Prev
    Next
    INDEX
    Explanations

    proper nouns or words with a capital letter used in formal contexts like political discourse, technical manuals or medical texts

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    PreExecute
    -0.56
    PickerController
    -0.53
     Venise
    -0.50
     AssemblyTitle
    -0.49
    hapsody
    -0.48
    bedingt
    -0.48
    OuterClass
    -0.47
    ときに
    -0.46
     coussin
    -0.46
    <<(
    -0.46
    POSITIVE LOGITS
    everything
    0.94
    every
    0.86
    Everything
    0.84
    EVERY
    0.84
     every
    0.83
     everything
    0.82
    Semua
    0.80
    Tutti
    0.80
     Everything
    0.79
    throughout
    0.78
    Activations Density 23.533%

    No Known Activations