© 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. 4778
    Prev
    Next
    INDEX
    Explanations

    terms related to slavery, race, and historical discussions of racial dynamics.

    oai_token-act-pair · gemini-2.0-flash

    slave trade

    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
     surla
    -0.80
    دانشنامهٔ
    -0.73
     CreateTagHelper
    -0.72
     Offisielt
    -0.68
     للاسماء
    -0.68
     iprot
    -0.68
    XmlAccessType
    -0.68
    UVWXYZ
    -0.65
     发表于
    -0.64
    TagHelper
    -0.63
    POSITIVE LOGITS
     MaterialApp
    0.47
    bolista
    0.46
     pro
    0.45
    ISupport
    0.43
    oblastoma
    0.43
    Collegamenti
    0.41
     flat
    0.41
     culture
    0.41
     application
    0.40
     thromb
    0.40
    Activations Density 11.044%

    No Known Activations