© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4353
    Prev
    Next
    INDEX
    Explanations

    LaTeX and C++ code snippets

    oai_token-act-pair · gemini-2.0-flash

    code with math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    <eos>
    -0.51
    fm
    -0.43
     нав
    -0.42
    Link
    -0.40
    um
    -0.39
    semantics
    -0.39
    multirow
    -0.38
    GEBURTS
    -0.38
     exti
    -0.38
    匹
    -0.38
    POSITIVE LOGITS
    PerformLayout
    0.73
    windowFixed
    0.71
     automatiques
    0.70
     preſent
    0.69
    InitVars
    0.68
    edipus
    0.67
     متعلقه
    0.66
     TabLayout
    0.66
    المكان
    0.66
     الوطنيه
    0.62
    Activations Density 1.445%

    No Known Activations