© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13803
    Prev
    Next
    INDEX
    Explanations

    mentions of Denmark and associated historical terms

    oai_token-act-pair · gemini-2.0-flash

    Denmark and Schleswig

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     carteira
    -0.45
     beginnetje
    -0.43
    anto
    -0.43
    keyed
    -0.42
    נצ
    -0.42
     depo
    -0.42
     ejus
    -0.41
     cle
    -0.41
     (;;)
    -0.40
    tai
    -0.40
    POSITIVE LOGITS
     TestBed
    0.72
    tvguidetime
    0.69
    WithMany
    0.67
    ########.
    0.67
     defaultstate
    0.65
     ModelExpression
    0.65
    PerformLayout
    0.64
     viewDidLoad
    0.61
    licability
    0.60
     nakalista
    0.60
    Activations Density 1.676%

    No Known Activations