© 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. 13027
    Prev
    Next
    INDEX
    Explanations

    concluding remarks and references to research material

    oai_token-act-pair · gemini-2.0-flash

    conclusion/contribution

    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
     stá
    -0.44
    WebpackPlugin
    -0.43
     him
    -0.42
     
    -0.40
     However
    -0.38
    newArrayList
    -0.38
    <0xBC>
    -0.38
     ${
    -0.37
    beforeEach
    -0.37
     Read
    -0.37
    POSITIVE LOGITS
    rungsseite
    0.85
     disambiguazione
    0.76
    Geplaatst
    0.75
     immemorial
    0.74
    %");
    0.73
    AddHtmlAttribute
    0.73
    NOPQRST
    0.71
    Datuak
    0.71
     BrowserModule
    0.71
    labus
    0.70
    Activations Density 2.469%

    No Known Activations