© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12452
    Prev
    Next
    INDEX
    Explanations

    words related to games or weapons

    oai_token-act-pair · gemini-2.0-flash

    game playing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     myſelf
    -0.91
     itſelf
    -0.86
    ſelf
    -0.78
     themſelves
    -0.78
     himſelf
    -0.75
     uſe
    -0.72
     cauſe
    -0.70
    ſelves
    -0.69
     pleaſure
    -0.68
     faſt
    -0.68
    POSITIVE LOGITS
     հղումներ
    0.56
    ngrx
    0.53
    XmlAccessType
    0.48
     TestBed
    0.48
    SpringBootTest
    0.47
    rophe
    0.47
    iços
    0.45
     ra
    0.45
    WebVitals
    0.44
    argument
    0.44
    Activations Density 2.375%

    No Known Activations