© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4035
    Prev
    Next
    INDEX
    Explanations

    names followed by commas

    oai_token-act-pair · gemini-2.0-flash

    Document snippets

    np_max-act-logits · 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
    Negative Logits
     <<<<<<<<<<<<<<
    -0.60
    IBar
    -0.50
     nonatomic
    -0.50
    ">—
    -0.49
     CURIAM
    -0.48
    setVerticalGroup
    -0.47
    machus
    -0.47
    chila
    -0.45
    PHeader
    -0.44
    nonatomic
    -0.43
    POSITIVE LOGITS
    NOPQRST
    0.60
    Искәрмәләр
    0.57
     Winaray
    0.54
     Olímpicos
    0.53
     contextLoads
    0.52
    jsdelivr
    0.52
     Italijanski
    0.51
     المعيارى
    0.50
     calendriers
    0.50
     BoxFit
    0.49
    Activations Density 6.861%

    No Known Activations