© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7756
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and related terms with some possible bias towards closed or circular shapes

    oai_token-act-pair · gemini-2.0-flash

    circles and loops

    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
    DockStyle
    -0.82
    SizeF
    -0.80
     propOrder
    -0.78
     ModelExpression
    -0.77
     Roskov
    -0.72
    tonsoft
    -0.71
    glGen
    -0.69
     ujednoznacz
    -0.68
    Geplaatst
    -0.65
    +:+
    -0.65
    POSITIVE LOGITS
     circle
    1.38
     circles
    1.36
     loop
    1.21
    Circle
    1.17
     circuit
    1.16
     Circle
    1.15
     loops
    1.13
     circling
    1.13
     round
    1.12
    circle
    1.11
    Activations Density 1.355%

    No Known Activations