© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1486
    Prev
    Next
    INDEX
    Explanations

    changes in roles and employment, often using the word "to"

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     سكانية
    -0.63
     arşivlendi
    -0.63
     referenties
    -0.62
     charge
    -0.59
    reportWebVitals
    -0.57
     ligiloj
    -0.56
    WithIOException
    -0.55
     CURIAM
    -0.53
     Charge
    -0.50
    Sucesor
    -0.49
    POSITIVE LOGITS
     head
    0.60
    complexContent
    0.60
     незавершена
    0.56
    ekš
    0.55
    HasAnnotation
    0.55
    PhysRevD
    0.54
    head
    0.54
    emlrt
    0.52
    SequentialGroup
    0.52
     surla
    0.51
    Activations Density 8.669%

    No Known Activations