© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9238
    Prev
    Next
    INDEX
    Explanations

    a large variety of numeric data, from code variable names to sports scores.

    oai_token-act-pair · gemini-2.0-flash

    scientific data

    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
     AssemblyCulture
    -1.15
    MENAFN
    -1.05
     GenerationType
    -1.05
     kaarangay
    -0.97
    ImageContext
    -0.93
     iſt
    -0.92
     auffi
    -0.91
     Jefus
    -0.90
    HtmlAttribute
    -0.89
     becauſe
    -0.89
    POSITIVE LOGITS
     re
    0.44
     put
    0.41
     set
    0.41
     de
    0.41
     dem
    0.39
     sw
    0.38
     trans
    0.37
     shut
    0.36
     not
    0.36
     P
    0.35
    Activations Density 3.822%

    No Known Activations