© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14697
    Prev
    Next
    INDEX
    Explanations

    the use of numbers and counting in a context of authority or facts

    oai_token-act-pair · gemini-2.0-flash

    Tourism

    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
     tourism
    -1.13
     tourist
    -1.12
    tourism
    -1.05
    tourist
    -1.04
    Tourism
    -1.04
    Tourist
    -1.02
     Tourist
    -1.02
     tourists
    -1.02
     Tourism
    -1.01
     turística
    -1.00
    POSITIVE LOGITS
     arrivals
    0.54
     PEC
    0.49
    arri
    0.48
     inbound
    0.47
     outbound
    0.47
    ssil
    0.47
    fold
    0.47
    Crossref
    0.46
    Angelina
    0.46
     lips
    0.45
    Activations Density 0.740%

    No Known Activations