© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6523
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to 3D graphics and game physics concepts, especially collision detection and spatial organization

    oai_token-act-pair · gemini-2.0-flash

    Computer code and algorithms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     OK
    -0.64
    ValueStyle
    -0.62
     ok
    -0.60
    OK
    -0.57
     close
    -0.56
    modal
    -0.55
     pop
    -0.52
     okay
    -0.51
    close
    -0.51
    ReusableCell
    -0.51
    POSITIVE LOGITS
    HttpPut
    0.64
    </tfoot>
    0.61
     nakalista
    0.60
    ❹
    0.59
    calaureate
    0.59
    setViewportView
    0.57
     despe
    0.57
     getItemId
    0.57
    TagMode
    0.56
     auffi
    0.55
    Activations Density 3.544%

    No Known Activations