© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3278
    Prev
    Next
    INDEX
    Explanations

    words related to the domain of sports, science, medicine, fiction, politics, business, and apparel.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     AssemblyTitle
    -0.68
     resourceCulture
    -0.64
    stdc
    -0.63
    enterOuterAlt
    -0.62
    fillType
    -0.59
    HomeAsUpEnabled
    -0.59
    setVerticalGroup
    -0.59
    
    -0.59
    TabIndex
    -0.57
    bobox
    -0.56
    POSITIVE LOGITS
     _("
    0.57
     Nesse
    0.56
     Quindi
    0.53
     lokalen
    0.52
     dreamstime
    0.52
    Quindi
    0.51
     noastre
    0.49
    ureusement
    0.49
     følgende
    0.49
     "..\..\..\
    0.49
    Activations Density 17.784%

    No Known Activations