© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4721
    Prev
    Next
    INDEX
    Explanations

    scientific or medical papers that include the word 'that'

    oai_token-act-pair · gemini-2.0-flash

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    RectangleBorder
    -0.68
    WithIOException
    -0.67
     purpoſe
    -0.67
     Anſ
    -0.67
    InputBorder
    -0.67
     itſelf
    -0.67
     Diſ
    -0.66
     فريبيس
    -0.66
    addContainerGap
    -0.65
     Efq
    -0.65
    POSITIVE LOGITS
    Życiorys
    0.73
    mesine
    0.56
    '));
    0.54
    tedy
    0.53
    charCodeAt
    0.52
    하여
    0.52
     thereby
    0.52
    canestro
    0.52
    flashdata
    0.51
    iddle
    0.51
    Activations Density 0.577%

    No Known Activations