© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12647
    Prev
    Next
    INDEX
    Explanations

    content about American and Native American history, especially stories of conflict

    oai_token-act-pair · gemini-2.0-flash

    terms related to historical context and Native Americans

    np_token-act-pair-logits · gpt-4o-mini

    American settlement/colonial history

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    twimg
    -0.63
    נטרנט
    -0.49
     CreateTagHelper
    -0.48
     بيها
    -0.48
    ]._
    -0.47
     surla
    -0.47
    σιν
    -0.47
    ьаж
    -0.47
    ContextHolder
    -0.46
     Meksiku
    -0.46
    POSITIVE LOGITS
    IsMutable
    0.70
    ScopeManager
    0.57
    elemField
    0.51
    getColumnIndex
    0.50
     voyageurs
    0.48
     tribes
    0.48
    clase
    0.48
     cross
    0.47
    pulumi
    0.47
    GIH
    0.47
    Activations Density 7.260%

    No Known Activations