© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12254
    Prev
    Next
    INDEX
    Explanations

    words and phrases in game development contexts, especially related to game state, interface and statistics

    oai_token-act-pair · gemini-2.0-flash

    game resources

    np_max-act-logits · 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
     vectoriales
    -0.52
    endsection
    -0.48
    onViewCreated
    -0.48
     literaria
    -0.47
     derajat
    -0.46
     scolaires
    -0.46
     محفوظة
    -0.46
     kaynağından
    -0.45
     vettore
    -0.45
     चुनें
    -0.43
    POSITIVE LOGITS
    Personendaten
    0.76
     gold
    0.69
    省市镇
    0.65
    gold
    0.61
     Gold
    0.60
    eakers
    0.57
    tovers
    0.57
    /−
    0.57
    InMillis
    0.57
     resources
    0.56
    Activations Density 1.110%

    No Known Activations