© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2135
    Prev
    Next
    INDEX
    Explanations

    words relating to the description, study, or writing of technical or scientific processes

    oai_token-act-pair · gemini-2.0-flash

    used

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    QMetaType
    -0.63
    ########.
    -0.54
    خانه
    -0.51
     /\.(
    -0.48
    rašymas
    -0.47
     Paglinawan
    -0.47
    Unmanaged
    -0.47
    setColumn
    -0.46
    setupUi
    -0.46
    nall
    -0.45
    POSITIVE LOGITS
     used
    1.98
    Used
    1.88
     Used
    1.84
    used
    1.81
     use
    1.81
     USED
    1.66
     usage
    1.62
     Use
    1.59
     utilized
    1.59
    Use
    1.56
    Activations Density 3.773%

    No Known Activations