© 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. 4022
    Prev
    Next
    INDEX
    Explanations

    words related to computer networks, routing and protocols, but also picks up other technical jargon

    oai_token-act-pair · gemini-2.0-flash

    computer networks/protocols

    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
     MonoBehaviour
    -0.51
     يتيمه
    -0.48
    хьтан
    -0.48
    ècie
    -0.47
    useEffect
    -0.47
     eset
    -0.46
    URUS
    -0.45
    ,:);
    -0.45
     estekak
    -0.45
     Schre
    -0.45
    POSITIVE LOGITS
    Expose
    0.63
     saites
    0.60
     layers
    0.57
    MigrationBuilder
    0.57
    Transparent
    0.57
    MLLoader
    0.57
     gran
    0.57
     transparent
    0.56
    UnknownFieldSet
    0.55
     Pollen
    0.54
    Activations Density 5.603%

    No Known Activations