© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9537
    Prev
    Next
    INDEX
    Explanations

    references to the game Candy Crush

    oai_token-act-pair · gemini-2.0-flash

    specific terms related to games

    np_token-act-pair-logits · gpt-4o-mini

    online games and downloads

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     خارجية
    -0.65
    complexType
    -0.61
    ActionCreators
    -0.57
    Pyx
    -0.55
     végét
    -0.52
    
    -0.52
     Joplin
    -0.52
     ExecuteAsync
    -0.51
     Paglinawan
    -0.50
     [/
    -0.50
    POSITIVE LOGITS
    ритори
    0.49
    govine
    0.49
     FormControl
    0.45
     transfieras
    0.43
    ValueStyle
    0.43
     Maze
    0.43
    seende
    0.43
    ocyclic
    0.43
    Демографія
    0.43
     Forge
    0.42
    Activations Density 2.508%

    No Known Activations