© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15648
    Prev
    Next
    INDEX
    Explanations

    terms related to video games, especially racing and adventure games.

    oai_token-act-pair · gemini-2.0-flash

    games, racing, sports

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ValueStyle
    -0.66
     CURIAM
    -0.66
    databind
    -0.59
     fubject
    -0.58
    deacon
    -0.56
    BeginInit
    -0.55
    btnNew
    -0.55
     fusca
    -0.54
     quæ
    -0.54
     المعيارى
    -0.54
    POSITIVE LOGITS
    saraba
    0.47
     kaynağından
    0.46
     hinaus
    0.46
    RP
    0.40
    chained
    0.39
     Audiodateien
    0.39
     Stacks
    0.39
    SpringBoot
    0.39
     Trink
    0.38
     infancia
    0.38
    Activations Density 3.518%

    No Known Activations