© 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. 6895
    Prev
    Next
    INDEX
    Explanations

    phrases about refusal to obey orders

    oai_token-act-pair · gemini-2.0-flash

    orders, commands

    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
    cplusplus
    -0.52
    RegressionTest
    -0.49
    Kjelder
    -0.47
    ⓘ
    -0.47
    Datuak
    -0.46
     apologised
    -0.46
    İstinadlar
    -0.44
    الحياه
    -0.44
     tabi
    -0.44
    XmlAccessType
    -0.44
    POSITIVE LOGITS
     orders
    1.69
     command
    1.56
     commands
    1.53
     order
    1.47
     Orders
    1.42
     Order
    1.35
    order
    1.32
     instructions
    1.31
    orders
    1.31
    Order
    1.31
    Activations Density 1.392%

    No Known Activations