© 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. 4821
    Prev
    Next
    INDEX
    Explanations

    words ending in "graph", "graphic", or "graphical", especially those related to scholarly fields like demography or biography and medical imaging.

    oai_token-act-pair · gemini-2.0-flash

    graph

    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
     ujednoznacz
    -0.65
    SequentialGroup
    -0.65
    $_['
    -0.63
     autorytatywna
    -0.63
     INTERESAR
    -0.61
    TabIndex
    -0.59
     transfieras
    -0.59
    bibitem
    -0.58
    InjectAttribute
    -0.57
    ValueStyle
    -0.55
    POSITIVE LOGITS
    graph
    1.09
     graphic
    1.09
    gra
    1.09
     Graph
    1.06
     graph
    1.05
    Graph
    1.04
     GRAPH
    1.03
    graf
    1.02
    Graphic
    1.02
     Graphic
    1.02
    Activations Density 1.782%

    No Known Activations