© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4738
    Prev
    Next
    INDEX
    Explanations

    the word "capable" and related words, especially in technical texts

    oai_token-act-pair · gemini-2.0-flash

    capable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     the
    -0.90
    ly
    -0.89
     
    -0.89
     most
    -0.79
     more
    -0.79
     The
    -0.76
     use
    -0.72
     early
    -0.71
     only
    -0.71
     in
    -0.68
    POSITIVE LOGITS
     Roskov
    1.60
    ValueStyle
    1.29
     AssemblyCulture
    1.29
    ViewFeatures
    1.23
    djangoproject
    1.22
    تقاوى
    1.21
     resourceCulture
    1.20
     defaultstate
    1.18
    QMetaType
    1.17
    GEBURTSDATUM
    1.17
    Activations Density 3.729%

    No Known Activations