© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14191
    Prev
    Next
    INDEX
    Explanations

    a concatenation of affixes implying backward or repeated actions/states.

    oai_token-act-pair · gemini-2.0-flash

    Technical/Academic Text

    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
    ymce
    -0.72
    hesus
    -0.63
    asuring
    -0.58
    brtc
    -0.57
    RegressionTest
    -0.57
    lining
    -0.56
     esterni
    -0.56
    ToTensor
    -0.55
    úrese
    -0.55
    ophen
    -0.55
    POSITIVE LOGITS
     betweenstory
    0.59
    featureID
    0.55
    WaitGroup
    0.48
     CommonModule
    0.47
     BorderRadius
    0.47
    theless
    0.43
     <=",
    0.42
    AnchorStyles
    0.41
     lạc
    0.41
     iprot
    0.41
    Activations Density 1.894%

    No Known Activations