© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4462
    Prev
    Next
    INDEX
    Explanations

    a long sequence of words related to tea parties and food, along with movie mistakes.

    oai_token-act-pair · gemini-2.0-flash

    dishware

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    principalTable
    -0.87
    OGND
    -0.80
    RegressionTest
    -0.70
    AndEndTag
    -0.65
     nakalista
    -0.65
    astify
    -0.59
    ThroughAttribute
    -0.59
    SharedCtor
    -0.57
     AssemblyTitle
    -0.56
    PerformLayout
    -0.56
    POSITIVE LOGITS
    avajillas
    0.63
     urmă
    0.54
     Agust
    0.52
     ouvido
    0.50
     Aussch
    0.48
    plish
    0.48
    vum
    0.46
    cheibe
    0.46
     crochê
    0.45
     gênero
    0.45
    Activations Density 1.314%

    No Known Activations