© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10747
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with advertising, campaigns, and outreach, particularly through digital and/or social media

    oai_token-act-pair · gemini-2.0-flash

    Internet content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    RTGC
    -0.47
     head
    -0.47
     Cabral
    -0.46
     mili
    -0.46
     machete
    -0.46
     body
    -0.45
    jong
    -0.45
    gebung
    -0.45
    бель
    -0.44
     start
    -0.44
    POSITIVE LOGITS
    SequentialGroup
    1.03
     GenerationType
    0.84
    parsedMessage
    0.79
    featureID
    0.78
    protoimpl
    0.66
     iprot
    0.66
     onData
    0.64
    "]));
    0.64
    !")
    0.63
    matchCondition
    0.63
    Activations Density 2.038%

    No Known Activations