© 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. 3854
    Prev
    Next
    INDEX
    Explanations

    a mix of code, personal pronouns, and colors, specifically the color red

    oai_token-act-pair · gemini-2.0-flash

    say "space-prefixed"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     =
    -0.56
     +=
    -0.55
    ant
    -0.54
    M
    -0.54
    </td>
    -0.53
     (…)
    -0.53
    E
    -0.53
     –
    -0.52
     &&
    -0.52
    dom
    -0.51
    POSITIVE LOGITS
    <bos>
    1.58
    SourceChecksum
    1.05
    :✨
    0.91
    stdc
    0.87
    InjectAttribute
    0.85
     '\\;'
    0.81
    
    0.80
     للمعارف
    0.79
    ulongan
    0.79
    setupUi
    0.77
    Activations Density 4.146%

    No Known Activations