© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5822
    Prev
    Next
    INDEX
    Explanations

    discourse markers

    oai_token-act-pair · gemini-2.0-flash

    furthermore, moreover

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     so
    -0.45
     teda
    -0.42
    katapos
    -0.40
     However
    -0.39
     Cependant
    -0.38
     насеље
    -0.38
     thus
    -0.38
    Sure
    -0.38
    herself
    -0.37
    habad
    -0.37
    POSITIVE LOGITS
    GEBURTSDATUM
    0.93
    Personensuche
    0.84
     resourceCulture
    0.82
    ValueStyle
    0.76
    parsedMessage
    0.76
    writeFieldEnd
    0.75
    webElementXpaths
    0.74
     they
    0.74
    tagHelperRunner
    0.73
    AddTagHelper
    0.71
    Activations Density 3.412%

    No Known Activations