© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9818
    Prev
    Next
    INDEX
    Explanations

    content about sports results, including scores, dates, and rankings

    oai_token-act-pair · gemini-2.0-flash

    zero

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    apunov
    -0.47
    Kalb
    -0.47
    XtraGrid
    -0.45
     nakalista
    -0.43
    フル
    -0.43
     shopping
    -0.42
     препратки
    -0.41
     Himo
    -0.41
    ilit
    -0.40
    hdashline
    -0.40
    POSITIVE LOGITS
    expandindo
    0.86
    ///</
    0.77
    出版年
    0.73
    BeginInit
    0.71
    memoized
    0.68
    MethodType
    0.67
    SharedCtor
    0.67
    دانشنامهٔ
    0.66
    SourceChecksum
    0.66
    بوابة
    0.64
    Activations Density 0.620%

    No Known Activations