© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1462
    Prev
    Next
    INDEX
    Explanations

    a variety of different proper nouns

    oai_token-act-pair · gemini-2.0-flash

    code and technical text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Source
    -0.60
    app
    -0.57
    YE
    -0.54
     Den
    -0.50
     DN
    -0.50
     Source
    -0.49
     hashCode
    -0.48
    />
    -0.48
    ellers
    -0.47
    九
    -0.47
    POSITIVE LOGITS
     "..\..\..\
    0.77
    Abitanti
    0.74
    HasIndex
    0.73
     kasarigan
    0.69
    SourceChecksum
    0.68
    jooq
    0.63
     "..\..\
    0.63
    Rohy
    0.62
    Espèce
    0.61
     AssemblyProduct
    0.60
    Activations Density 0.318%

    No Known Activations