© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12053
    Prev
    Next
    INDEX
    Explanations

    C/C++ code syntax including variable types, pointers, structs, commands, system calls, and string literals.

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    esModule
    -0.78
    دانشنامهٔ
    -0.74
    Билгалдахарш
    -0.70
    CloseOperation
    -0.66
    EndGlobalSection
    -0.63
    SBATCH
    -0.63
    RTGC
    -0.63
    IsContent
    -0.60
     BIBSYS
    -0.60
    <?>>
    -0.60
    POSITIVE LOGITS
    aliers
    0.43
    setopt
    0.43
    ArrayAdapter
    0.43
    HandlerContext
    0.42
     betweenstory
    0.41
    ɲ
    0.41
     vertrouwen
    0.40
     voordeel
    0.38
    läufer
    0.38
    PerPage
    0.38
    Activations Density 1.959%

    No Known Activations