© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15392
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to medical terminology, scientific studies, and comparisons.

    oai_token-act-pair · gemini-2.0-flash

    biological/medical studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -0.84
    interopRequire
    -0.83
     nahilalakip
    -0.78
    +#+#
    -0.74
    matchCondition
    -0.72
     uintptr
    -0.70
    DispatchToProps
    -0.69
    Personendaten
    -0.69
    tagHelperRunner
    -0.67
    complexContent
    -0.65
    POSITIVE LOGITS
    umque
    0.53
     Leder
    0.51
    Климат
    0.47
    rawdę
    0.46
    </thead>
    0.45
    Demografia
    0.44
     anyag
    0.42
    żeli
    0.42
    теризу
    0.42
    łku
    0.41
    Activations Density 2.380%

    No Known Activations