© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11553
    Prev
    Next
    INDEX
    Explanations

    words that have a long vowel sound followed by several consonants

    oai_token-act-pair · gemini-2.0-flash

    conduct

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     CreateTagHelper
    -0.57
    vang
    -0.56
     Researchers
    -0.54
     Scientists
    -0.52
     Data
    -0.52
     kasarigan
    -0.52
     vz
    -0.51
    Hale
    -0.51
     insert
    -0.51
    heb
    -0.50
    POSITIVE LOGITS
    conducted
    0.78
    Conduct
    0.76
    Extensive
    0.70
     conducted
    0.69
     Conduct
    0.68
    conduct
    0.68
     Extensive
    0.67
     conduct
    0.67
     conducting
    0.66
     Conducted
    0.66
    Activations Density 1.245%

    No Known Activations