© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3845
    Prev
    Next
    INDEX
    Explanations

    collocations of technical terms and identifiers for accessing resources

    oai_token-act-pair · gemini-2.0-flash

    programming terms and technical jargon

    np_token-act-pair-logits · gpt-4o-mini

    scientific genomics data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     velkommen
    -0.50
    forKey
    -0.49
     Dig
    -0.45
     fond
    -0.44
     Digital
    -0.43
     digital
    -0.43
    printLine
    -0.43
     Jard
    -0.43
    delivery
    -0.42
    digital
    -0.42
    POSITIVE LOGITS
    Hochspringen
    0.69
    tagHelperRunner
    0.69
    esez
    0.69
    AccessorTable
    0.68
     odkazy
    0.66
    Спасылкі
    0.61
    saraba
    0.61
     facie
    0.60
     onOptions
    0.59
    ArrowToggle
    0.58
    Activations Density 0.812%

    No Known Activations