© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5640
    Prev
    Next
    INDEX
    Explanations

    code-related keywords, possibly configuration- or hardware-related

    oai_token-act-pair · gemini-2.0-flash

    config

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    config
    -2.27
     config
    -2.08
    Config
    -1.97
     Config
    -1.74
    CONFIG
    -1.35
    getConfig
    -1.13
     CONFIG
    -1.13
     configs
    -1.09
    configs
    -1.05
    Configs
    -1.03
    POSITIVE LOGITS
    Captor
    0.60
    TemporalType
    0.56
    UnusedPrivate
    0.55
    protoimpl
    0.50
    apimachinery
    0.50
    THISDAY
    0.50
    InjectAttribute
    0.50
    GraphicsUnit
    0.49
     Walkover
    0.49
     defaultstate
    0.47
    Activations Density 0.102%

    No Known Activations