© 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. 13893
    Prev
    Next
    INDEX
    Explanations

    contextual discourse markers, references to time, and statements of opinion.

    oai_token-act-pair · gemini-2.0-flash

    moment

    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
    ˈ
    -0.70
    lis
    -0.48
    li
    -0.48
    ku
    -0.48
    ing
    -0.47
    ulis
    -0.46
    XtraEditors
    -0.45
    module
    -0.45
     special
    -0.44
    MD
    -0.44
    POSITIVE LOGITS
    ViewImports
    0.85
    rikes
    0.73
    انيف
    0.71
     fédé
    0.69
     myſelf
    0.69
    ngths
    0.68
     roulant
    0.68
     OMITBAD
    0.66
    ackerel
    0.66
     purpoſe
    0.65
    Activations Density 18.945%

    No Known Activations