© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7671
    Prev
    Next
    INDEX
    Explanations

    a mix of the word "open", HTML blockquotes and the last syllables of some people's last names

    oai_token-act-pair · gemini-2.0-flash

    Math and tennis context

    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
    <blockquote>
    -0.91
    etern
    -0.52
    초
    -0.52
     شر
    -0.47
     oídos
    -0.45
    DebuggerNonUser
    -0.45
    InSection
    -0.45
    🎓
    -0.44
     Trou
    -0.44
    featureID
    -0.44
    POSITIVE LOGITS
    <bos>
    1.92
    yntaxException
    0.66
    %@",
    0.62
     Monfieur
    0.60
    reportWebVitals
    0.59
     perſon
    0.58
     againſt
    0.57
     itſelf
    0.57
     ſy
    0.56
     houſe
    0.56
    Activations Density 0.291%

    No Known Activations