© 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. 11466
    Prev
    Next
    INDEX
    Explanations

    code that uses the System class

    oai_token-act-pair · gemini-2.0-flash

    System

    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
    RenderAtEndOf
    -0.82
    ftagPool
    -0.79
    __*/
    -0.79
    StructEnd
    -0.68
    PerformLayout
    -0.67
    انيف
    -0.57
    جراء
    -0.57
    chkin
    -0.57
    adda
    -0.56
    اعي
    -0.56
    POSITIVE LOGITS
     ujednoznacz
    0.56
    
    0.55
     disponibilités
    0.44
    OwnProperty
    0.43
    bní
    0.42
     endif
    0.42
     discretionary
    0.42
    ConfigureAwait
    0.41
    XmlAccessorType
    0.41
     geslacht
    0.39
    Activations Density 0.099%

    No Known Activations