© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11911
    Prev
    Next
    INDEX
    Explanations

    language commonly found in legal documents, including mentions of time, actions, and arguments.

    oai_token-act-pair · gemini-2.0-flash

    legal cases

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     CreateTagHelper
    -0.80
    UnusedPrivate
    -0.72
    IUrlHelper
    -0.71
    Diweddarwch
    -0.68
     pinulongan
    -0.68
    PreferredItem
    -0.67
     AssemblyProduct
    -0.66
    WithIOException
    -0.66
     Biôgrafia
    -0.66
     Roskov
    -0.64
    POSITIVE LOGITS
     service
    0.57
     Service
    0.51
    apic
    0.50
     ]];
    0.49
    FTFY
    0.49
     SERVICE
    0.47
    wechs
    0.47
    Service
    0.45
     servizio
    0.43
     partida
    0.43
    Activations Density 0.484%

    No Known Activations