© 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. 16013
    Prev
    Next
    INDEX
    Explanations

    numerical data, especially those involving measurement units and currency

    oai_token-act-pair · gemini-2.0-flash

    meter

    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
     oprot
    -0.86
     مرئيه
    -0.61
     getItemId
    -0.61
    rawDesc
    -0.59
     transfieras
    -0.59
    IUrlHelper
    -0.57
    hundred
    -0.57
     LoggerFactory
    -0.57
     inflater
    -0.56
    DispatchToProps
    -0.55
    POSITIVE LOGITS
     m
    1.13
    m
    1.06
     м
    0.71
    ｍ
    0.71
     Met
    0.66
    met
    0.65
    Met
    0.64
     meter
    0.63
    M
    0.63
    м
    0.63
    Activations Density 1.662%

    No Known Activations