© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2534
    Prev
    Next
    INDEX
    Explanations

    variations of the phrase "lead to"

    oai_token-act-pair · gemini-2.0-flash

    occurrences of the word 'lead'

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

    say "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_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
    ScopeManager
    -0.78
    writeFieldEnd
    -0.62
    AccessorTable
    -0.60
    جستارهای
    -0.59
    IMPORTED
    -0.59
    تقاوى
    -0.58
    erweise
    -0.58
    躇
    -0.58
    [*]
    -0.57
    AutoresizingMask
    -0.57
    POSITIVE LOGITS
     to
    0.85
    IContainer
    0.50
     Americans
    0.49
     hikariConfig
    0.42
     barata
    0.42
    InlineData
    0.42
     useAppContext
    0.42
     esterni
    0.41
     trå
    0.41
     örgü
    0.41
    Activations Density 2.631%

    No Known Activations