© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11946
    Prev
    Next
    INDEX
    Explanations

    fragments of research paper citations, including journal name abbreviations, volume numbers, page ranges, and years of publication, and code snippets with file names and line numbers

    oai_token-act-pair · gemini-2.0-flash

    Technical documents and numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     برانيه
    -0.67
    irited
    -0.66
    }{*}{
    -0.61
    zeß
    -0.57
     MainAxisSize
    -0.53
     nemlig
    -0.51
    ajn
    -0.50
    帖最后由
    -0.50
    wahati
    -0.47
    Šaltiniai
    -0.46
    POSITIVE LOGITS
    use
    0.66
    argout
    0.59
    uses
    0.59
    access
    0.57
    webElementXpaths
    0.56
    1
    0.56
     mapStateToProps
    0.55
    SpringBootTest
    0.55
     للاسماء
    0.53
     Allociné
    0.52
    Activations Density 8.814%

    No Known Activations