© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15912
    Prev
    Next
    INDEX
    Explanations

    phrases including "all"

    oai_token-act-pair · gemini-2.0-flash

    things and everything

    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
    Décès
    -0.47
    はじめに
    -0.47
    bukkit
    -0.44
    äť
    -0.42
     Emissions
    -0.42
     diman
    -0.40
    lementation
    -0.39
    WebServlet
    -0.38
    jectable
    -0.38
    Dmit
    -0.38
    POSITIVE LOGITS
     things
    1.11
    Things
    1.05
     Things
    1.02
    things
    0.98
     everything
    0.95
     THINGS
    0.95
     thing
    0.94
     told
    0.93
    everything
    0.84
     Everything
    0.84
    Activations Density 0.745%

    No Known Activations