© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13720
    Prev
    Next
    INDEX
    Explanations

    scientific language describing the methodology or results of experiments

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    UPI
    -0.53
    Rhestr
    -0.52
    angi
    -0.52
    Gemeinden
    -0.51
    LinkId
    -0.51
     AppCompatTheme
    -0.50
    nsis
    -0.50
    LayoutStyle
    -0.50
    batis
    -0.49
    TestingModule
    -0.49
    POSITIVE LOGITS
    olesale
    0.64
    ICAGO
    0.62
     InputDecoration
    0.59
     vidare
    0.57
     OnEnable
    0.55
    ')['
    0.52
    værende
    0.52
     initComponents
    0.52
    oluene
    0.52
     Outer
    0.52
    Activations Density 7.061%

    No Known Activations