© 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. 9878
    Prev
    Next
    INDEX
    Explanations

    code snippets with keywords that involve loading files, handling errors, and querying categories

    oai_token-act-pair · gemini-2.0-flash

    load

    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
    ↵↵
    -0.54
     the
    -0.54
    ↵
    -0.50
    a
    -0.49
    <td>
    -0.48
     Race
    -0.47
     The
    -0.47
    壮
    -0.47
    <tr>
    -0.46
     "
    -0.46
    POSITIVE LOGITS
     nahilalakip
    1.04
    basicConfig
    1.02
    EndGlobalSection
    1.01
    parsedMessage
    1.00
     estekak
    0.96
    complexContent
    0.94
    WebVitals
    0.93
    AndEndTag
    0.93
    ագրություններ
    0.91
     EconPapers
    0.90
    Activations Density 0.641%

    No Known Activations