© 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. 15062
    Prev
    Next
    INDEX
    Explanations

    proper nouns followed by titles or descriptions of position

    oai_token-act-pair · gemini-2.0-flash

    Job titles

    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
    cupertino
    -0.44
    ılmıştır
    -0.42
    suri
    -0.41
    xaml
    -0.41
    itori
    -0.41
    readFileSync
    -0.41
    pperware
    -0.40
     للتو
    -0.40
     BorderSide
    -0.40
    {`
    -0.38
    POSITIVE LOGITS
     Head
    2.11
     head
    2.06
    Head
    1.94
     Chief
    1.75
     Director
    1.67
     chief
    1.67
    Chief
    1.66
     Executive
    1.56
     HEAD
    1.55
    head
    1.53
    Activations Density 4.660%

    No Known Activations