© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2797
    Prev
    Next
    INDEX
    Explanations

    mentions of Playstation consoles

    oai_token-act-pair · gemini-2.0-flash

    PlayStation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    WriteAttribute
    -0.60
    Itoa
    -0.56
    styleUrls
    -0.55
    GeneratedMessage
    -0.52
     ویکی‌پدیای
    -0.50
     Bologna
    -0.49
    interopRequire
    -0.48
     Rua
    -0.48
    OLVED
    -0.48
    detectChanges
    -0.47
    POSITIVE LOGITS
    tráfico
    0.58
    })();
    0.57
    ogaster
    0.56
     AppColors
    0.54
     continúas
    0.52
     Limit
    0.51
     limit
    0.50
    futbolista
    0.49
    chyma
    0.47
    Fibre
    0.46
    Activations Density 3.421%

    No Known Activations