© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 12046
    Prev
    Next
    INDEX
    Explanations

    words related to physical systems, energy, medicine, buildings, and measurement of them

    oai_token-act-pair · gemini-2.0-flash

    technical terms or components related to systems

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

    Technical systems and devices

    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
    ış
    -0.51
    WriteLiteral
    -0.46
    jamientos
    -0.43
     }^{(
    -0.43
     {[
    -0.43
     Ones
    -0.42
     BIBSYS
    -0.42
     pulumi
    -0.42
    elek
    -0.42
     Più
    -0.42
    POSITIVE LOGITS
    ArrowToggle
    0.91
    CloseOperation
    0.79
     وتسجيلات
    0.73
     often
    0.72
    onAttach
    0.71
    انجليز
    0.69
     typically
    0.68
    ngrx
    0.66
     usually
    0.65
    LabelTagHelper
    0.64
    Activations Density 2.718%

    No Known Activations