© 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
    2. Gemma-2-2B
    3. 23-GEMMASCOPE-TRANSCODER-16K
    4. 13703
    Prev
    Next
    INDEX
    Explanations

    the text is in German, and the neuron seems to be looking for the German word for "the"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    TagMode
    -0.70
    windowFixed
    -0.68
    WithMany
    -0.61
    AddTagHelper
    -0.61
    BufferException
    -0.54
    KURZBESCHREIBUNG
    -0.53
    ioutil
    -0.52
    NewGuid
    -0.50
    expandindo
    -0.50
    AnimationsModule
    -0.49
    POSITIVE LOGITS
    
    0.52
     utafitiHapana
    0.52
    ền
    0.52
     matur
    0.50
     بيها
    0.49
     ویکی‌پدیای
    0.49
    Fontes
    0.47
     deven
    0.47
     Gram
    0.47
    Por
    0.46
    Activations Density 0.364%

    No Known Activations