© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4421
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and code snippets

    oai_token-act-pair · gemini-2.0-flash

    set operations

    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
    contentLoaded
    -0.70
    Hentet
    -0.64
     StatefulWidget
    -0.63
    Referanser
    -0.57
     numberWith
    -0.53
    resizingMask
    -0.51
    IBOutlet
    -0.50
    (;;)
    -0.49
    Glej
    -0.48
    ISupport
    -0.48
    POSITIVE LOGITS
     union
    1.23
     Union
    1.07
     UNION
    1.05
     intersection
    1.05
    Union
    1.02
    union
    0.97
    UNION
    0.91
     intersect
    0.91
     Intersection
    0.86
    intersect
    0.84
    Activations Density 4.461%

    No Known Activations