© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11321
    Prev
    Next
    INDEX
    Explanations

    code snippets containing programming constructs, e.g., variable assignments, directory structures, and queries

    oai_token-act-pair · gemini-2.0-flash

    code and file paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    #
    -0.52
     autorytatywna
    -0.42
    <h2>
    -0.40
    ズム
    -0.37
     åren
    -0.37
     noblesse
    -0.37
     Tode
    -0.36
     osten
    -0.36
    Blk
    -0.35
    Traditional
    -0.34
    POSITIVE LOGITS
    tangentMode
    0.76
    <bos>
    0.72
    BeginContext
    0.70
    Referències
    0.68
    DockStyle
    0.63
     חיצוניים
    0.63
    moiselle
    0.62
    ButtonModule
    0.60
     AssemblyProduct
    0.60
     VizieR
    0.57
    Activations Density 20.004%

    No Known Activations