© 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. 6229
    Prev
    Next
    INDEX
    Explanations

    food menu items and their descriptions.

    oai_token-act-pair · gemini-2.0-flash

    dressing

    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
     sanitarias
    -0.47
    pannt
    -0.46
     riport
    -0.45
     piele
    -0.45
    ждую
    -0.44
     المتحدة
    -0.44
     piese
    -0.43
     Tamaño
    -0.43
     unidade
    -0.43
    gangenen
    -0.42
    POSITIVE LOGITS
    الحياه
    0.91
    NameInMap
    0.77
    Geplaatst
    0.77
    transQ
    0.75
     '\\;'
    0.74
    abestanden
    0.73
     BoxFit
    0.73
    verifyException
    0.69
    WriteBarrier
    0.65
     onCreateView
    0.63
    Activations Density 1.756%

    No Known Activations