© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13899
    Prev
    Next
    INDEX
    Explanations

    courtroom terminology and legal language

    oai_token-act-pair · gemini-2.0-flash

    documents/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_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
    +#+#
    -1.03
    Personensuche
    -0.93
    Autoritní
    -0.91
     autorytatywna
    -0.88
    elemField
    -0.87
     viewDidLoad
    -0.84
    脚注の使い方
    -0.84
    UnusedPrivate
    -0.83
    contentLoaded
    -0.83
     resourceCulture
    -0.82
    POSITIVE LOGITS
     in
    0.43
     actively
    0.41
     with
    0.40
     by
    0.39
     alter
    0.38
    atil
    0.37
     as
    0.37
     for
    0.36
     active
    0.36
    initely
    0.36
    Activations Density 2.767%

    No Known Activations