© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7126
    Prev
    Next
    INDEX
    Explanations

    organization-related words and phrases

    oai_token-act-pair · gemini-2.0-flash

    construction industry

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     bidet
    -0.59
     Grundstück
    -0.57
     sièges
    -0.56
     ground
    -0.56
     đất
    -0.56
     tripod
    -0.55
     paddock
    -0.55
     AssemblyCulture
    -0.54
     foundations
    -0.54
    WireFormat
    -0.52
    POSITIVE LOGITS
     الحره
    1.01
    ">//
    0.60
     trade
    0.59
    Халык
    0.57
    trade
    0.55
    Tembelea
    0.55
    DebuggerNonUser
    0.54
     estekak
    0.53
     initComponents
    0.52
     فريبيس
    0.52
    Activations Density 0.657%

    No Known Activations