© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11669
    Prev
    Next
    INDEX
    Explanations

    things related to war and conflict, particularly in the context of WWII.

    oai_token-act-pair · gemini-2.0-flash

    WWII concentration camps

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     fumée
    -0.52
    muri
    -0.52
    RAEL
    -0.49
    __);
    -0.48
     âmes
    -0.48
    AGEM
    -0.46
     Hire
    -0.45
     AssemblyTitle
    -0.45
    DispatchToProps
    -0.45
     stabilité
    -0.45
    POSITIVE LOGITS
     Мексичка
    0.69
    tagHelperRunner
    0.62
     autorytatywna
    0.59
    lapsingToolbar
    0.57
     concentration
    0.57
    ScopeManager
    0.55
    脚注の使い方
    0.55
    FailureListener
    0.55
     Había
    0.54
    utnik
    0.54
    Activations Density 1.135%

    No Known Activations