© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12750
    Prev
    Next
    INDEX
    Explanations

    bracketed numbers in the text, possibly citations or references

    oai_token-act-pair · gemini-2.0-flash

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    צלחה
    -0.51
    Datuak
    -0.50
    MemoryWarning
    -0.47
     pitié
    -0.47
    eseorang
    -0.47
    føre
    -0.47
    føring
    -0.47
     touristique
    -0.47
    tonode
    -0.46
    Fordítás
    -0.46
    POSITIVE LOGITS
     AssemblyCulture
    0.92
    
    0.72
    Personensuche
    0.62
     AssemblyProduct
    0.59
    yntaxException
    0.57
    idex
    0.57
    NameInMap
    0.56
     tục
    0.56
    bonucle
    0.56
    DrawerToggle
    0.54
    Activations Density 1.253%

    No Known Activations