© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5602
    Prev
    Next
    INDEX
    Explanations

    dots after certain characters (probably, but not definitely, periods in Java code)

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    CodedInputStream
    -0.71
    posedge
    -0.68
    pædia
    -0.62
    WebServlet
    -0.57
    setupUi
    -0.54
     endforeach
    -0.54
    SharedCtor
    -0.53
     leſs
    -0.52
     SqlDbType
    -0.51
     Majefty
    -0.51
    POSITIVE LOGITS
    AddTagHelper
    0.59
    ArrowToggle
    0.56
    writeFieldEnd
    0.54
    contentLoaded
    0.50
    出版年
    0.45
     tendenza
    0.45
    GOTREF
    0.45
     reposer
    0.44
     disambiguazione
    0.44
    Спољашње
    0.44
    Activations Density 0.083%

    No Known Activations