© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 10917
    Prev
    Next
    INDEX
    Explanations

    phrases with multiple capitalized words, potentially titles or headings

    oai_token-act-pair · gemini-2.0-flash

    Basic concepts

    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
     Subpart
    -0.82
     Adjacent
    -0.76
    Chham
    -0.76
     Cluster
    -0.75
    InitVars
    -0.74
     Segment
    -0.74
     Precinct
    -0.74
     Branch
    -0.72
     Subcommittee
    -0.70
     Consortium
    -0.69
    POSITIVE LOGITS
     Money
    0.90
     Music
    0.88
    Money
    0.76
     Food
    0.76
     News
    0.73
    Music
    0.73
     Pain
    0.73
     Love
    0.73
     Weather
    0.72
     Blood
    0.71
    Activations Density 7.733%

    No Known Activations