© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12468
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to gospel music, slave spirituals, or old-timey vernacular

    oai_token-act-pair · gemini-2.0-flash

    day

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    KommentareTeilen
    -0.70
    AutoresizingMask
    -0.69
     BoxFit
    -0.64
     виправивши
    -0.60
     φύ
    -0.59
    spur
    -0.57
    ."],
    -0.55
    ++
    -0.55
    among
    -0.55
    Xaml
    -0.53
    POSITIVE LOGITS
    XmlAccessType
    0.61
    DispatchToProps
    0.58
    SourceChecksum
    0.52
    Personendaten
    0.50
    jsxFileName
    0.46
     мәкал
    0.46
    tagHelperRunner
    0.45
     szóci
    0.45
     ویکی‌پدیا
    0.45
     հղումներ
    0.45
    Activations Density 0.111%

    No Known Activations