© 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
    2. Gemma-2-2B
    3. 3-GEMMASCOPE-TRANSCODER-16K
    4. 7299
    Prev
    Next
    INDEX
    Explanations

    words related to legal and medical texts, especially when 'backed' or 'bysical' are mentioned

    oai_token-act-pair · gemini-2.0-flash

    legal/medical support/evidence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    stateProvider
    -0.64
    RectangleBorder
    -0.59
    AnimationsModule
    -0.57
    SupportActionBar
    -0.57
    +#+#
    -0.55
     Bayard
    -0.54
     effectually
    -0.54
     &___
    -0.54
     ReactDOM
    -0.54
     SwiftUI
    -0.54
    POSITIVE LOGITS
    cambrian
    0.54
    ostante
    0.53
    FontOfSize
    0.51
    FixedSize
    0.51
    hôte
    0.51
    insegna
    0.50
    为止
    0.49
     meeste
    0.48
     afgelopen
    0.48
     referenties
    0.47
    Activations Density 1.525%

    No Known Activations