© 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. 5624
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially Python code, and is potentially related to web APIs or server requests and responses

    oai_token-act-pair · gemini-2.0-flash

    datatypes

    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
    FormTagHelper
    -0.76
     تضيفلها
    -0.73
    MessageTagHelper
    -0.69
    WithIOException
    -0.69
    ніципа
    -0.68
    (;;)
    -0.64
     Italijani
    -0.63
     Italijanski
    -0.63
     Infórmanos
    -0.62
    /**
    -0.62
    POSITIVE LOGITS
     f
    0.96
    f
    0.90
    str
    0.69
    int
    0.69
     int
    0.63
     F
    0.63
     str
    0.60
    F
    0.58
     True
    0.58
     round
    0.57
    Activations Density 2.339%

    No Known Activations