© 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. 9544
    Prev
    Next
    INDEX
    Explanations

    legal and legislative terminology.

    oai_token-act-pair · gemini-2.0-flash

    legal texts

    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
    SharedDtor
    -1.25
     AssemblyCulture
    -1.09
     ExecuteAsync
    -1.03
     ujednoznacz
    -1.01
    Personendaten
    -1.00
    parsedMessage
    -0.99
     Мексичка
    -0.99
    IVEREF
    -0.97
     esternos
    -0.97
    IUrlHelper
    -0.97
    POSITIVE LOGITS
     foli
    0.43
     code
    0.39
    ent
    0.37
    微
    0.37
    std
    0.36
    malloc
    0.35
    twig
    0.35
    augh
    0.34
     laiko
    0.33
     Code
    0.33
    Activations Density 2.548%

    No Known Activations