© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6539
    Prev
    Next
    INDEX
    Explanations

    words associated with the potential dangers of railroad crossings

    oai_token-act-pair · gemini-2.0-flash

    driving-related terms

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

    driving

    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
     pinulongan
    -0.44
    offsetof
    -0.38
    fton
    -0.38
    ItemGroup
    -0.38
    cznie
    -0.38
     amiss
    -0.37
    toHaveBeenCalled
    -0.37
    Ἁ
    -0.37
    pson
    -0.37
    woosh
    -0.36
    POSITIVE LOGITS
    verwijspagina
    0.82
     Drivers
    0.73
     Passing
    0.69
    driving
    0.68
     hitting
    0.67
     passing
    0.66
     Driving
    0.66
    StructEnd
    0.66
     drivers
    0.65
     Driver
    0.65
    Activations Density 4.823%

    No Known Activations