© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6351
    Prev
    Next
    INDEX
    Explanations

    words related to science and technology

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     greater
    -0.83
     easier
    -0.82
     stronger
    -0.77
    Easier
    -0.74
    Greater
    -0.72
     better
    -0.71
     safer
    -0.71
    Хьажоргаш
    -0.71
    easier
    -0.69
     brighter
    -0.69
    POSITIVE LOGITS
     invokingState
    0.65
    CodeAttribute
    0.59
    RepeatedField
    0.52
    Scrolled
    0.51
    BackgroundImage
    0.49
     שוליים
    0.49
     Majefty
    0.48
     suficientemente
    0.48
     Commencez
    0.47
    Glej
    0.46
    Activations Density 11.836%

    No Known Activations