© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10492
    Prev
    Next
    INDEX
    Explanations

    words or phrases that often come right before or after action verbs

    oai_token-act-pair · gemini-2.0-flash

    forms of the verb 'view'

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

    view

    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
    Билгалдахарш
    -0.61
    TestingModule
    -0.58
    TagHelper
    -0.54
    нциклопедия
    -0.51
    horabuena
    -0.50
     betweenstory
    -0.49
    UnusedPrivate
    -0.49
     sumpay
    -0.48
    makeConstraints
    -0.48
    RegistryLite
    -0.47
    POSITIVE LOGITS
     seen
    2.30
     view
    2.13
     viewed
    2.08
     View
    1.83
    view
    1.80
    seen
    1.79
     Seen
    1.78
    View
    1.77
     VIEW
    1.73
     views
    1.69
    Activations Density 2.522%

    No Known Activations