© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14627
    Prev
    Next
    INDEX
    Explanations

    words, phrases, and names related to historical events and figures, and often highlights specific details like dates and locations within historical narratives.

    oai_token-act-pair · gemini-2.0-flash

    military campaigns

    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
     ResponseEntity
    -0.58
    Externé
    -0.57
     صوتيه
    -0.56
     jsPsych
    -0.55
     FormsModule
    -0.52
     الرياضيه
    -0.52
    migrationBuilder
    -0.52
     propriété
    -0.51
     démocratie
    -0.49
    asteroide
    -0.49
    POSITIVE LOGITS
    Chham
    0.56
    bootstrapcdn
    0.55
    ньому
    0.53
     campaign
    0.51
    henko
    0.51
    ViewImports
    0.49
    MENAFN
    0.48
    Besos
    0.47
    ledem
    0.47
    InitVars
    0.46
    Activations Density 2.141%

    No Known Activations