© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 868
    Prev
    Next
    INDEX
    Explanations

    words followed or preceded by "the", calls to action, and certain proper nouns.

    oai_token-act-pair · gemini-2.0-flash

    calling something

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    出版年
    -0.67
     raiſ
    -0.61
    httphttps
    -0.60
     himſelf
    -0.58
    Erreferentziak
    -0.57
    ToBounds
    -0.57
     gevolg
    -0.57
     lenker
    -0.55
     snippetHide
    -0.55
     Eſ
    -0.54
    POSITIVE LOGITS
    aarrggbb
    0.60
    piram
    0.52
    Bibliografía
    0.50
     RECORD
    0.50
     الرياضيه
    0.50
    ématique
    0.50
     −
    0.50
    ARIUS
    0.49
     **)
    0.48
    Largest
    0.48
    Activations Density 14.804%

    No Known Activations