© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11883
    Prev
    Next
    INDEX
    Explanations

    This neuron detects snippets of computer code or mark-up, and legal/political conspiracy terminology from the right wing.

    oai_token-act-pair · gemini-2.0-flash

    internet controversies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    ValueStyle
    -0.63
    StoryboardSegue
    -0.61
    SetBool
    -0.56
    ServletException
    -0.56
    fortawesome
    -0.51
    BarStyle
    -0.49
     Huffington
    -0.49
     defStyle
    -0.47
    SqlClient
    -0.47
     يتيمه
    -0.47
    POSITIVE LOGITS
    ciaż
    0.66
    tanleria
    0.60
     мәкал
    0.57
    CloseOperation
    0.57
    <bos>
    0.55
    GEBURTS
    0.55
    isticated
    0.54
    rophoresis
    0.54
    geted
    0.52
    HasAnnotation
    0.52
    Activations Density 0.085%

    No Known Activations