© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4000
    Prev
    Next
    INDEX
    Explanations

    This neuron activates for a wide variety of apparently unrelated terms making it hard to pin down a specific purpose

    oai_token-act-pair · gemini-2.0-flash

    Formal/Scientific writing

    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
    Negative Logits
     brought
    -0.51
    Cartney
    -0.48
    stdc
    -0.46
     sav
    -0.46
     dra
    -0.46
     m
    -0.45
    roir
    -0.45
    <!--[
    -0.44
     l
    -0.44
     used
    -0.44
    POSITIVE LOGITS
     myſelf
    1.01
     Theſe
    0.89
     itſelf
    0.85
    RenderAtEndOf
    0.85
     himſelf
    0.84
     Monfieur
    0.83
     ModelExpression
    0.82
    Diwedd
    0.81
     שוליים
    0.81
     themſelves
    0.80
    Activations Density 2.189%

    No Known Activations