© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10152
    Prev
    Next
    INDEX
    Explanations

    various code snippets including variable declarations, functions, and SQL statements

    oai_token-act-pair · gemini-2.0-flash

    code and database queries

    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
    "]:
    -0.45
    tou
    -0.45
     BB
    -0.45
    "]
    -0.42
    }>
    -0.41
     Ro
    -0.41
    isen
    -0.41
     claim
    -0.40
    rag
    -0.40
     tou
    -0.40
    POSITIVE LOGITS
     HasFactory
    0.91
    AccessorTable
    0.79
    XmlAccessorType
    0.76
    NameInMap
    0.75
    GraphicsUnit
    0.74
     مشين
    0.73
    RenderAtEndOf
    0.72
    SuppressMessage
    0.70
    bootstrapcdn
    0.70
     NSCoder
    0.69
    Activations Density 2.426%

    No Known Activations