© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5765
    Prev
    Next
    INDEX
    Explanations

    mathematical articles or equations, particularly discussing directed graphs and edges

    oai_token-act-pair · gemini-2.0-flash

    graph edges

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    NameInMap
    -0.82
    حياتها
    -0.59
    utilisons
    -0.56
     surla
    -0.56
     Bourgoin
    -0.51
     übere
    -0.49
    ]));
    -0.48
     NotImplemented
    -0.48
     Autorizaciones
    -0.47
    |')
    -0.47
    POSITIVE LOGITS
     edge
    0.85
    GRAPH
    0.82
    edge
    0.82
    Edge
    0.81
    graph
    0.80
     edges
    0.80
     graph
    0.79
     Edge
    0.79
    EDGE
    0.77
    Edges
    0.72
    Activations Density 2.802%

    No Known Activations