© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12058
    Prev
    Next
    INDEX
    Explanations

    mentions of geographic regions and administrative districts, particularly in Poland, as well as the concept of "rally."

    oai_token-act-pair · gemini-2.0-flash

    Place names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     дописавши
    -0.79
    Geplaatst
    -0.75
     AssemblyTitle
    -0.72
    rungsseite
    -0.66
     BoxDecoration
    -0.66
    ContentAsync
    -0.65
     againſt
    -0.65
    EndGlobalSection
    -0.65
     itſelf
    -0.65
    GeoNames
    -0.64
    POSITIVE LOGITS
    CodeAttribute
    0.46
    begin
    0.46
     st
    0.43
    asi
    0.40
    zine
    0.36
     Halen
    0.36
     rowspan
    0.36
     lecteur
    0.35
    nalités
    0.34
     up
    0.34
    Activations Density 0.209%

    No Known Activations