© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12710
    Prev
    Next
    INDEX
    Explanations

    snippets of text from scientific-sounding papers containing mathematical formulas as well as some other unrelated text

    oai_token-act-pair · gemini-2.0-flash

    code/equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    abetes
    -0.73
     Theſe
    -0.58
     leçons
    -0.57
    AddHtmlAttribute
    -0.57
     فريبيس
    -0.56
     colorés
    -0.56
     Anſ
    -0.55
     étend
    -0.55
     Nantucket
    -0.55
    Selanjutnya
    -0.54
    POSITIVE LOGITS
    VersionUID
    0.70
     defaultstate
    0.68
    CPtr
    0.66
    FontStyle
    0.55
     @"/
    0.54
     AssemblyProduct
    0.53
    wor
    0.52
    thâu
    0.51
    出版年
    0.51
    UrlResolution
    0.51
    Activations Density 13.095%

    No Known Activations