© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1080
    Prev
    Next
    INDEX
    Explanations

    LaTeX math mode syntax

    oai_token-act-pair · gemini-2.0-flash

    Latex symbols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    avl
    -0.57
    (',
    -0.56
    .,
    -0.56
    哉
    -0.52
    scala
    -0.51
     ',
    -0.51
     ",";
    -0.51
     ,\
    -0.51
    /',
    -0.51
    /,
    -0.51
    POSITIVE LOGITS
     snippetHide
    0.66
    enumi
    0.65
    uxxxx
    0.64
     ModelExpression
    0.64
    parsedMessage
    0.60
     propOrder
    0.58
     kaarangay
    0.58
    AccessorTable
    0.56
    yntaxException
    0.56
    awtextra
    0.55
    Activations Density 2.978%

    No Known Activations