© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3846
    Prev
    Next
    INDEX
    Explanations

    sketching, drawing, tracing and dot connections

    oai_token-act-pair · gemini-2.0-flash

    sketching or tracing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    IsContent
    -0.59
    HasAnnotation
    -0.59
    enderror
    -0.59
    exprimer
    -0.54
    NSNotification
    -0.54
    bitField
    -0.54
    SourceChecksum
    -0.52
    couver
    -0.52
    Mui
    -0.51
    havior
    -0.50
    POSITIVE LOGITS
     drawing
    0.87
     Drawing
    0.83
     sketch
    0.79
     sketches
    0.76
     Draws
    0.75
     sketching
    0.75
    sketch
    0.75
     DRAWING
    0.71
     drawn
    0.70
    Draws
    0.70
    Activations Density 1.782%

    No Known Activations