© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 396
    Prev
    Next
    INDEX
    Explanations

    research analyses and their methodologies.

    oai_token-act-pair · gemini-2.0-flash

    research methods

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    #+#
    -0.91
     itſelf
    -0.83
    ſelf
    -0.81
     Efq
    -0.78
     Reſ
    -0.78
     Houſe
    -0.76
     nahilalakip
    -0.76
     propOrder
    -0.75
    ſelves
    -0.75
     reaſon
    -0.74
    POSITIVE LOGITS
     mass
    0.64
     HPLC
    0.63
     PCR
    0.60
     qPCR
    0.56
     Mass
    0.55
    mass
    0.55
    HPLC
    0.55
     Western
    0.54
     confocal
    0.54
     Fourier
    0.53
    Activations Density 4.895%

    No Known Activations