© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16123
    Prev
    Next
    INDEX
    Explanations

    dates and references to airplanes

    oai_token-act-pair · gemini-2.0-flash

    World War I trenches

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    RenderAtEndOf
    -0.79
    ArgsConstructor
    -0.72
    Espèce
    -0.68
    LabelTagHelper
    -0.66
    Portail
    -0.66
     BrowserModule
    -0.63
     незавершена
    -0.61
    AutoresizingMask
    -0.61
    InputTagHelper
    -0.60
     MainAxisSize
    -0.60
    POSITIVE LOGITS
     trench
    0.49
     Great
    0.49
     First
    0.49
    tren
    0.48
     WIB
    0.46
     trenches
    0.46
     Erster
    0.45
    Tren
    0.44
     Ersten
    0.44
     vorbe
    0.44
    Activations Density 0.908%

    No Known Activations