© 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. 8386
    Prev
    Next
    INDEX
    Explanations

    durations of time marked in hours or days

    oai_token-act-pair · gemini-2.0-flash

    units of time

    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
    rétaire
    -0.43
     utilisons
    -0.40
    égard
    -0.39
    keyDown
    -0.38
     pukul
    -0.38
    lifetime
    -0.38
    неопр
    -0.38
     au
    -0.36
    Dominique
    -0.36
     lifetime
    -0.35
    POSITIVE LOGITS
    principalColumn
    0.75
     intptr
    0.73
     nakalista
    0.73
    IntoConstraints
    0.73
    ########.
    0.73
    imageshack
    0.71
    ValueStyle
    0.69
    исленность
    0.68
     EconPapers
    0.66
     ImportError
    0.65
    Activations Density 1.127%

    No Known Activations