© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11558
    Prev
    Next
    INDEX
    Explanations

    connections to the UK, Brexit and Europe

    oai_token-act-pair · gemini-2.0-flash

    European politics

    np_max-act-logits · 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
    saraba
    -0.64
    BufferException
    -0.62
    UnknownFieldSet
    -0.58
    σθαι
    -0.56
    pazität
    -0.55
     {*}
    -0.54
    دانشنامهٔ
    -0.54
    blauch
    -0.54
     quæ
    -0.53
    しゃれ
    -0.52
    POSITIVE LOGITS
    CrossRef
    0.66
    قایناقلار
    0.60
     autorytatywna
    0.54
    drawn
    0.54
     виправивши
    0.52
    AddTagHelper
    0.52
    Παραπομπές
    0.51
     Th
    0.50
    umat
    0.50
    RunAsync
    0.48
    Activations Density 1.931%

    No Known Activations