© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6743
    Prev
    Next
    INDEX
    Explanations

    sections of chat logs where users are giving each other basic instructions about computers

    oai_token-act-pair · gemini-2.0-flash

    internet chat log

    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
     sur
    -0.93
    sur
    -0.79
    Sur
    -0.69
     his
    -0.63
     SUR
    -0.60
     Sur
    -0.60
     their
    -0.58
    SUR
    -0.57
     تضيفلها
    -0.50
    Their
    -0.49
    POSITIVE LOGITS
     son
    0.74
     sa
    0.71
     AssemblyCulture
    0.69
     mapStateToProps
    0.67
    sa
    0.65
    InjectAttribute
    0.65
    Son
    0.63
     Son
    0.62
    DispatchToProps
    0.60
    ItemBackground
    0.59
    Activations Density 0.547%

    No Known Activations