© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10335
    Prev
    Next
    INDEX
    Explanations

    This neuron seems to activate for terms related to industrial production and technical applications with an emphasis on automation.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    adze
    -0.43
     proposé
    -0.41
    jelder
    -0.39
    之助
    -0.39
     commerciales
    -0.39
     Consultez
    -0.38
    ègre
    -0.38
     mécan
    -0.37
    ваем
    -0.37
     cận
    -0.36
    POSITIVE LOGITS
    rungsseite
    0.81
     GenerationType
    0.81
    FieldBuilder
    0.77
     OFDb
    0.74
     >=",
    0.71
     ProtoMessage
    0.71
    Portail
    0.69
    ')")
    0.67
    hould
    0.66
    +#+#
    0.66
    Activations Density 2.670%

    No Known Activations