© 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. 9859
    Prev
    Next
    INDEX
    Explanations

    statistical information such as measurements, numbers, and scores

    oai_token-act-pair · gemini-2.0-flash

    numbers

    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
     AssemblyProduct
    -0.56
    GBT
    -0.54
    Cyfeiriadau
    -0.53
    greenrobot
    -0.49
     Protobuf
    -0.48
     Marley
    -0.47
    SystemColors
    -0.45
    Ҭ
    -0.44
    SerializeField
    -0.44
    prechpartner
    -0.43
    POSITIVE LOGITS
    UNRELATED
    0.78
     createContext
    0.74
    исленность
    0.74
     neuf
    0.69
     docked
    0.68
     Ninth
    0.66
     nine
    0.65
    ExtendWith
    0.65
    семь
    0.65
     Tenth
    0.65
    Activations Density 3.270%

    No Known Activations