© 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. 8206
    Prev
    Next
    INDEX
    Explanations

    number sequences with hyphens and sometimes colons

    oai_token-act-pair · gemini-2.0-flash

    Dashes

    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
     attached
    -0.60
    attached
    -0.59
     attach
    -0.52
     attaching
    -0.48
    detach
    -0.47
     Attached
    -0.47
    attach
    -0.45
     attachments
    -0.44
    Attached
    -0.43
     costas
    -0.42
    POSITIVE LOGITS
     ModelExpression
    1.02
    setVerticalGroup
    0.95
     AssemblyProduct
    0.81
    verwijspagina
    0.80
    abestanden
    0.73
    OrNil
    0.72
    lapsingToolbar
    0.71
     تضيفلها
    0.71
    ftagPool
    0.68
    ंदीखरीदारी
    0.67
    Activations Density 1.562%

    No Known Activations