© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12908
    Prev
    Next
    INDEX
    Explanations

    technical and scientific terms

    oai_token-act-pair · gemini-2.0-flash

    technical topics

    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
    RegressionTest
    -0.85
    aarrggbb
    -0.72
     onOptions
    -0.69
     Wikidata
    -0.59
    MLLoader
    -0.59
     noDo
    -0.59
    brainly
    -0.57
    HasForeignKey
    -0.56
    ertos
    -0.56
    twimg
    -0.56
    POSITIVE LOGITS
    either
    0.59
    Neither
    0.58
     Between
    0.57
     wither
    0.54
    Either
    0.54
    Both
    0.53
    owohl
    0.52
     either
    0.52
     Neither
    0.52
    neither
    0.51
    Activations Density 6.106%

    No Known Activations