© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16188
    Prev
    Next
    INDEX
    Explanations

    The neuron looks for the word "the" in the context of government entities, finances and law and order.

    oai_token-act-pair · gemini-2.0-flash

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    JvmStatic
    -0.61
    Frida
    -0.50
    SourceChecksum
    -0.50
     autorytatywna
    -0.48
    HasKey
    -0.48
     ob
    -0.47
     Administrativna
    -0.45
    XmlAccessType
    -0.45
    AlterField
    -0.44
     Forza
    -0.44
    POSITIVE LOGITS
    bootstrapcdn
    0.77
     disambiguazione
    0.75
    новништво
    0.67
     تانيه
    0.58
    webElementXpaths
    0.58
    DataInputStream
    0.58
     Вікі
    0.57
    Portale
    0.56
    DebuggerNonUser
    0.55
    StateToProps
    0.54
    Activations Density 2.115%

    No Known Activations