© 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. 2940
    Prev
    Next
    INDEX
    Explanations

    This neuron seems to find sentences, especially ones near section breaks or headings, and may be related to historical or folklore topics.

    oai_token-act-pair · 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
     aussieht
    -0.39
    Parm
    -0.38
     dentelle
    -0.37
     réaliste
    -0.35
     teile
    -0.35
    faßt
    -0.35
     blå
    -0.35
     poches
    -0.35
     souha
    -0.33
     hendes
    -0.33
    POSITIVE LOGITS
    Autoritní
    0.90
    CodedInputStream
    0.90
    참고
    0.85
    queryInterface
    0.79
    tagHelperRunner
    0.79
     The
    0.77
     AssemblyVersion
    0.75
    Erstellt
    0.72
    MeasureSpec
    0.71
    SourceChecksum
    0.71
    Activations Density 4.912%

    No Known Activations