© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2113
    Prev
    Next
    INDEX
    Explanations

    decimal numbers, often with leading zeros

    oai_token-act-pair · gemini-2.0-flash

    decimals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ✨:
    -1.04
    AndEndTag
    -0.69
     Chwiliwch
    -0.69
     mergeFrom
    -0.66
     muualla
    -0.65
     houſe
    -0.65
    قایناقلار
    -0.60
     Houſe
    -0.59
    berdayakan
    -0.59
     Majefty
    -0.59
    POSITIVE LOGITS
    ModelAdmin
    0.64
    Datuak
    0.62
    sizeCache
    0.54
    paramref
    0.52
     c
    0.49
    UNCH
    0.49
     Chi
    0.48
    resizingMask
    0.48
     Che
    0.48
     chi
    0.48
    Activations Density 1.287%

    No Known Activations