© 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. 5639
    Prev
    Next
    INDEX
    Explanations

    mentions of a government revenue service

    oai_token-act-pair · gemini-2.0-flash

    service

    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
     service
    -2.63
     Service
    -2.38
    service
    -2.27
    Service
    -2.25
     SERVICE
    -2.20
    SERVICE
    -1.95
     servicio
    -1.73
     servizio
    -1.62
    ervice
    -1.60
     serviço
    -1.42
    POSITIVE LOGITS
     myſelf
    0.71
    InitStruct
    0.60
    NOPQRST
    0.60
     Theſe
    0.57
     againſt
    0.56
     CreateTagHelper
    0.56
     Esau
    0.55
    gdala
    0.54
     Footwear
    0.54
    atação
    0.54
    Activations Density 0.374%

    No Known Activations