© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9647
    Prev
    Next
    INDEX
    Explanations

    the word "morning"

    oai_token-act-pair · gemini-2.0-flash

    morning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    [++
    -0.60
    ClCompile
    -0.54
     Row
    -0.52
     EventArgs
    -0.52
    bootstrapcdn
    -0.51
    oung
    -0.50
     har
    -0.49
     beyond
    -0.47
    tade
    -0.47
    山市
    -0.47
    POSITIVE LOGITS
    <bos>
    1.26
     Monfieur
    1.13
     itſelf
    1.12
     myſelf
    1.11
     pleaſure
    1.04
     Jefus
    0.99
     himſelf
    0.99
     Efq
    0.95
    ſelf
    0.94
     Theſe
    0.93
    Activations Density 0.616%

    No Known Activations