© 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. 12952
    Prev
    Next
    INDEX
    Explanations

    numbers in a document, particularly those related to currency, technical specifications, or version numbers

    oai_token-act-pair · gemini-2.0-flash

    technical terms and tokens in programming contexts

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

    Code and technical configurations

    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
    ⓧ
    -0.75
    PORTS
    -0.60
    por
    -0.57
    IMP
    -0.54
    import
    -0.53
     importe
    -0.53
    PyErr
    -0.51
     Imp
    -0.51
    porte
    -0.51
    orteur
    -0.50
    POSITIVE LOGITS
    UnusedPrivate
    0.55
    leih
    0.53
    AntiForgeryToken
    0.53
     AssemblyCompany
    0.52
     resourceCulture
    0.52
    SpringRunner
    0.51
    twimg
    0.50
    findpost
    0.50
    libft
    0.49
     Waray
    0.48
    Activations Density 3.258%

    No Known Activations