© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5356
    Prev
    Next
    INDEX
    Explanations

    C programming code, including definitions, hexadecimal values, and bitwise operations

    oai_token-act-pair · gemini-2.0-flash

    code definitions

    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
     propOrder
    -0.91
    ArgsConstructor
    -0.90
     <>",
    -0.89
    InjectAttribute
    -0.88
    ContentAsync
    -0.85
     يتيمه
    -0.85
    NUMX
    -0.85
     typelib
    -0.84
    RegistryLite
    -0.83
    archiviato
    -0.83
    POSITIVE LOGITS
    led
    0.52
     General
    0.51
    geführten
    0.50
     Morning
    0.47
     SW
    0.46
     SD
    0.44
     general
    0.43
     portas
    0.43
     us
    0.43
     ch
    0.41
    Activations Density 29.890%

    No Known Activations