© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13721
    Prev
    Next
    INDEX
    Explanations

    html and javascript code snippets including tags, attributes, and URLs

    oai_token-act-pair · gemini-2.0-flash

    script

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    message
    -0.82
     message
    -0.73
    Message
    -0.70
     Message
    -0.65
     MESSAGE
    -0.62
     messaging
    -0.56
    MESSAGE
    -0.52
    󠁴
    -0.50
     Hidup
    -0.50
    Model
    -0.49
    POSITIVE LOGITS
    AddTagHelper
    0.96
    XmlAccessorType
    0.82
    bootstrapcdn
    0.81
    UnknownFieldSet
    0.79
    awtextra
    0.73
     surla
    0.71
    RetentionPolicy
    0.69
    rrggbb
    0.67
     autorytatywna
    0.66
    RunWith
    0.63
    Activations Density 1.260%

    No Known Activations