© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1697
    Prev
    Next
    INDEX
    Explanations

    words and phrases that might be titles or headings on web pages

    oai_token-act-pair · gemini-2.0-flash

    About

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    breos
    -0.52
    onucleotide
    -0.50
     reis
    -0.48
    chw
    -0.48
    OPLE
    -0.46
     gran
    -0.46
     move
    -0.45
    rı
    -0.45
     Prisma
    -0.45
     kim
    -0.44
    POSITIVE LOGITS
    MigrationBuilder
    0.81
    IndentedString
    0.66
     snippetHide
    0.65
     peggio
    0.63
    AndEndTag
    0.57
    tonode
    0.57
    neté
    0.57
    usercontent
    0.56
     habet
    0.55
     GenerationType
    0.54
    Activations Density 15.610%

    No Known Activations