© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5893
    Prev
    Next
    INDEX
    Explanations

    proper nouns followed by words related to events happening

    oai_token-act-pair · gemini-2.0-flash

    arrival

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     Efq
    -0.63
    gestone
    -0.63
    شهاد
    -0.62
     LoggerFactory
    -0.59
     AssemblyCompany
    -0.58
    WireFormatLite
    -0.55
    UnknownFields
    -0.55
    lusst
    -0.54
    encodeWith
    -0.54
    zzleHttp
    -0.54
    POSITIVE LOGITS
     arrives
    1.10
     arrive
    1.03
     arriving
    1.02
     arrived
    1.01
     arrival
    0.94
     visit
    0.91
    Arri
    0.90
     Arrive
    0.84
     visited
    0.84
     visits
    0.84
    Activations Density 0.773%

    No Known Activations