© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9472
    Prev
    Next
    INDEX
    Explanations

    words or phrases that occur in technical writing and reports

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    <bos>
    -1.63
     myſelf
    -0.68
     itſelf
    -0.67
     kasarigan
    -0.66
     Monfieur
    -0.64
    /*
    -0.62
    oredCriteria
    -0.59
     **/
    -0.59
     Shakspeare
    -0.58
    ьаж
    -0.57
    POSITIVE LOGITS
     BorderSide
    0.73
    makeText
    0.56
    estin
    0.55
    newswire
    0.53
    InSection
    0.50
    abstractmethod
    0.50
    MemoryWarning
    0.50
     /*#__
    0.49
    Rcpp
    0.48
     OnInit
    0.48
    Activations Density 29.535%

    No Known Activations