© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12874
    Prev
    Next
    INDEX
    Explanations

    This neuron seems to respond to various technical and scientific terms, including some mathematical notation, foreign language snippets related to communication or problem-solving, and terms associated with mechanical movement and manufacturing.

    oai_token-act-pair · gemini-2.0-flash

    scientific/technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     myſelf
    -0.88
     itſelf
    -0.88
     themſelves
    -0.79
     himſelf
    -0.74
     Theſe
    -0.71
     ſeveral
    -0.70
     ſhe
    -0.69
    󠁢
    -0.69
     theſe
    -0.68
     AssemblyTitle
    -0.67
    POSITIVE LOGITS
    ↵↵
    0.53
     series
    0.52
    ↵
    0.51
    fortawesome
    0.49
    TestingModule
    0.44
     
    0.42
     raised
    0.42
    disposing
    0.41
    ملة
    0.41
    -
    0.40
    Activations Density 4.053%

    No Known Activations