© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2832
    Prev
    Next
    INDEX
    Explanations

    scientific and medical texts describing methods to form preparations and formulations

    oai_token-act-pair · gemini-2.0-flash

    saliva and pharmaceutical compositions

    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
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.90
     дописавши
    -0.90
     conversions
    -0.82
     Conversions
    -0.81
    aarrggbb
    -0.79
     conversion
    -0.77
     Conversion
    -0.75
    Conversions
    -0.73
     '\\;'
    -0.73
     myſelf
    -0.72
    POSITIVE LOGITS
    fır
    0.52
     rilas
    0.47
     ROUT
    0.45
    itemBuilder
    0.45
     détruit
    0.45
     hø
    0.44
    acher
    0.44
    pendenti
    0.44
     ру
    0.44
    dő
    0.44
    Activations Density 2.331%

    No Known Activations