© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11334
    Prev
    Next
    INDEX
    Explanations

    C/C++ and C# datatypes and bitfield related keywords

    oai_token-act-pair · gemini-2.0-flash

    C code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    dafx
    -0.90
     CreateTagHelper
    -0.88
     contextLoads
    -0.83
    \{\\
    -0.81
    Datuak
    -0.79
    ReusableCell
    -0.77
     فريبيس
    -0.76
    NUMX
    -0.76
    contentLoaded
    -0.71
    WireFormatLite
    -0.71
    POSITIVE LOGITS
    1
    0.56
    수
    0.43
    ohs
    0.39
    tema
    0.37
     U
    0.37
    manera
    0.36
    ز
    0.36
     tred
    0.35
    canestro
    0.34
     Amp
    0.34
    Activations Density 1.338%

    No Known Activations