© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13547
    Prev
    Next
    INDEX
    Explanations

    words broadly related to technical, military, or engineering applications, or a discussion thereof (e.g. pertaining to radar, radio, systems and devices).

    oai_token-act-pair · gemini-2.0-flash

    telecommunications and military applications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Meksiku
    -0.56
    AddTagHelper
    -0.56
    WebpackPlugin
    -0.50
     <>",
    -0.49
     Catawiki
    -0.49
    lamic
    -0.48
    Portály
    -0.47
    хьтан
    -0.47
    romi
    -0.47
     betweenstory
    -0.47
    POSITIVE LOGITS
    Hentet
    0.65
    > 
    0.58
    nador
    0.56
    ITES
    0.54
    bulin
    0.52
    ษา
    0.51
    TargetException
    0.50
    tidase
    0.50
    WebMethod
    0.49
    PageModule
    0.48
    Activations Density 3.148%

    No Known Activations