© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1684
    Prev
    Next
    INDEX
    Explanations

    acknowledgements spoken between chat users, often related to time spent working on a project.

    oai_token-act-pair · gemini-2.0-flash

    prefixes related to various categories

    np_token-act-pair-logits · gpt-4o-mini

    multilingual 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_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ArgumentParser
    -0.61
     AssemblyCulture
    -0.61
     OFDb
    -0.54
    AnchorStyles
    -0.54
    JspWriter
    -0.53
    FXML
    -0.47
    PackageManager
    -0.46
    ])));
    -0.46
    ruptedException
    -0.45
    yards
    -0.45
    POSITIVE LOGITS
     quelcon
    0.67
     démocr
    0.61
     незавершена
    0.60
     précédents
    0.59
     normaux
    0.59
     alimentaires
    0.57
     anciens
    0.57
     médicaux
    0.57
     ennemis
    0.55
     supérieures
    0.52
    Activations Density 0.391%

    No Known Activations