© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8076
    Prev
    Next
    INDEX
    Explanations

    section headers and parts of formal papers and articles

    oai_token-act-pair · gemini-2.0-flash

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Road
    -0.81
    ///</
    -0.75
    Road
    -0.73
     noqa
    -0.73
    RTEX
    -0.71
     Watershed
    -0.69
     Earthquakes
    -0.68
    GEBURTSDATUM
    -0.63
     Shoreline
    -0.62
    Stream
    -0.61
    POSITIVE LOGITS
     Bonus
    0.60
    BagLayout
    0.53
     Label
    0.52
     Nom
    0.52
     Members
    0.52
     Merch
    0.50
     Perfume
    0.50
     Copy
    0.50
     Package
    0.50
     Quotes
    0.49
    Activations Density 15.324%

    No Known Activations