© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4218
    Prev
    Next
    INDEX
    Explanations

    references to periods of time

    oai_token-act-pair · gemini-2.0-flash

    before or after

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    //
    -0.62
    NameInMap
    -0.59
     Spital
    -0.58
     JAXBElement
    -0.57
    
    -0.56
     criss
    -0.55
    Rè
    -0.55
     LoggerFactory
    -0.55
    comuna
    -0.54
    Brooklyn
    -0.53
    POSITIVE LOGITS
    Browsable
    0.53
    Diwedd
    0.52
     the
    0.52
    SourceChecksum
    0.52
     '{@
    0.49
    Бахар
    0.48
    )|^{
    0.47
    viewDidLoad
    0.46
     newBuilder
    0.46
    endforeach
    0.45
    Activations Density 2.846%

    No Known Activations