© 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. 14321
    Prev
    Next
    INDEX
    Explanations

    text detailing college and post-graduate study

    oai_token-act-pair · gemini-2.0-flash

    graduate, grad

    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
     cherchés
    -0.67
    IntoConstraints
    -0.66
    verwijspagina
    -0.66
    setVerticalGroup
    -0.65
    таратура
    -0.61
    
    -0.55
    UnsafeEnabled
    -0.54
    Abitanti
    -0.54
    AndEndTag
    -0.53
    曖昧さ回避
    -0.53
    POSITIVE LOGITS
     graduate
    1.25
     grad
    1.13
    graduate
    1.02
     GRADUATE
    1.00
     Graduate
    0.95
    Graduate
    0.91
     Grad
    0.76
     law
    0.73
    grad
    0.71
     masters
    0.69
    Activations Density 3.819%

    No Known Activations