© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8440
    Prev
    Next
    INDEX
    Explanations

    words that are high in numerical value or adjectives used to describe size

    oai_token-act-pair · gemini-2.0-flash

    Quantity measurements

    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
     missing
    -0.60
    CGContext
    -0.51
    missing
    -0.51
    runOnUiThread
    -0.50
    XmlAccessType
    -0.50
     mis
    -0.50
     missed
    -0.49
     insufficient
    -0.49
     Mis
    -0.48
    Missing
    -0.47
    POSITIVE LOGITS
     disambiguazione
    0.80
     surla
    0.64
    رشف
    0.63
    ніципа
    0.63
    тьяна
    0.60
     başladı
    0.59
    astéroïdes
    0.59
    SourceChecksum
    0.58
    tanleria
    0.57
    MemoryWarning
    0.56
    Activations Density 1.189%

    No Known Activations