© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5662
    Prev
    Next
    INDEX
    Explanations

    pronouns

    oai_token-act-pair · gemini-2.0-flash

    Artist/performer roles

    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
     disambiguazione
    -0.60
     chré
    -0.60
    ngdoc
    -0.59
     AssemblyTitle
    -0.57
    fört
    -0.55
    XtraReports
    -0.54
     deschis
    -0.54
     diritti
    -0.54
     françaises
    -0.54
     särsk
    -0.54
    POSITIVE LOGITS
     peoples
    0.77
     artist
    0.69
    aarrggbb
    0.63
    __(/*!
    0.61
     songwriter
    0.60
     childrens
    0.59
     musician
    0.58
     opponent
    0.57
     lover
    0.57
     chef
    0.57
    Activations Density 2.090%

    No Known Activations