© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12804
    Prev
    Next
    INDEX
    Explanations

    sections describing author contributions to a published work

    oai_token-act-pair · gemini-2.0-flash

    contributions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    BeginInit
    -0.67
    osoba
    -0.63
    koneksi
    -0.62
    存于互联网档案馆
    -0.59
    Rhestr
    -0.59
    )։
    -0.58
    Mississippi
    -0.57
    etCode
    -0.57
    ].)
    -0.57
    tagHelperRunner
    -0.56
    POSITIVE LOGITS
     fidélité
    0.65
     appartiennent
    0.65
     renforcé
    0.63
    ThroughAttribute
    0.61
     AssemblyCompany
    0.60
    WithIOException
    0.60
     fidu
    0.60
    HtmlAttribute
    0.60
     dilan
    0.59
     copertura
    0.59
    Activations Density 0.191%

    No Known Activations