© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7112
    Prev
    Next
    INDEX
    Explanations

    mentions of Donald Trump and the cheating of people out of money.

    oai_token-act-pair · gemini-2.0-flash

    financial wrongdoing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    SharedCtor
    -0.79
    xase
    -0.76
    WithIOException
    -0.75
     Италијани
    -0.72
    FieldNumber
    -0.70
    DoubleQuotes
    -0.65
     oprot
    -0.63
     незавершена
    -0.58
    Dış
    -0.57
    หวัด
    -0.57
    POSITIVE LOGITS
    WriteAttribute
    0.58
     robbed
    0.57
     الرياضيه
    0.54
     pinch
    0.54
    UserScript
    0.52
     متحده
    0.50
     pockets
    0.48
    zyż
    0.48
     propOrder
    0.46
     lccn
    0.45
    Activations Density 1.298%

    No Known Activations