© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11998
    Prev
    Next
    INDEX
    Explanations

    Python code, specifically where `None` is used as a default argument

    oai_token-act-pair · gemini-2.0-flash

    Python code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    None
    -1.63
     None
    -1.55
     none
    -1.08
    none
    -1.01
    NONE
    -0.97
     NONE
    -0.91
     ninguno
    -0.74
     esternos
    -0.68
     OFDb
    -0.61
     keiner
    -0.59
    POSITIVE LOGITS
     FetchType
    0.61
     scurt
    0.60
    kegaard
    0.60
    PerformLayout
    0.59
    ArgsConstructor
    0.57
    zellen
    0.56
    BASELINE
    0.55
     ModelExpression
    0.54
    мум
    0.54
    WaitGroup
    0.53
    Activations Density 0.650%

    No Known Activations