© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4900
    Prev
    Next
    INDEX
    Explanations

    words, phrases, and formatting related to medical and scientific research, statistics, and reporting

    oai_token-act-pair · gemini-2.0-flash

    technical terms and study references

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

    Medical/scientific study follow-ups

    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
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.62
     disambiguazione
    -0.57
    InfoWindow
    -0.56
    
    -0.56
    kyrie
    -0.54
    IsContent
    -0.54
     catalogo
    -0.53
     precisione
    -0.51
    %[
    -0.50
    WireFormatLite
    -0.49
    POSITIVE LOGITS
    VersionUID
    0.57
     الاطلاع
    0.54
    EndInit
    0.52
    หร
    0.50
    DeleteBehavior
    0.49
    moduleName
    0.48
     mostrarán
    0.47
     courses
    0.47
    AutoScaleMode
    0.47
     study
    0.47
    Activations Density 8.676%

    No Known Activations