© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8034
    Prev
    Next
    INDEX
    Explanations

    historical references, focusing on the Civil War era, armies, and deaths.

    oai_token-act-pair · gemini-2.0-flash

    non-English terms

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

    Civil War

    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
    ingo
    -0.47
     Tro
    -0.44
    ResumeLayout
    -0.43
     preferências
    -0.42
     pro
    -0.42
    hoda
    -0.42
    frain
    -0.40
    氓
    -0.40
    Akira
    -0.40
     Serv
    -0.40
    POSITIVE LOGITS
     препратки
    0.90
     NSCoder
    0.77
    ArgsConstructor
    0.77
    UrlResolution
    0.74
     Administrativna
    0.70
    
    0.68
     الحره
    0.67
    الحياه
    0.66
    TypedDataSet
    0.66
    Життєпис
    0.64
    Activations Density 2.310%

    No Known Activations