© 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. 6350
    Prev
    Next
    INDEX
    Explanations

    words, phrases, and abbreviations commonly associated with video games and gaming culture

    oai_token-act-pair · 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
     Roskov
    -0.46
    keith
    -0.43
    Джерела
    -0.40
    DockStyle
    -0.39
     companions
    -0.39
    واری
    -0.38
    plet
    -0.38
    поль
    -0.37
    gyp
    -0.36
     BCS
    -0.36
    POSITIVE LOGITS
    AddTagHelper
    0.83
    Datuak
    0.82
    __':
    0.75
    __":
    0.70
    tagext
    0.70
     تانيه
    0.68
     NSCoder
    0.65
     دیکھیے
    0.64
    InjectAttribute
    0.63
    Бахар
    0.63
    Activations Density 1.732%

    No Known Activations