© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3233
    Prev
    Next
    INDEX
    Explanations

    the word "the" that is either at the beginning of the string or that has "on" preceding it

    oai_token-act-pair · gemini-2.0-flash

    the

    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
    encodeWith
    -0.57
     crainte
    -0.52
    Czytaj
    -0.50
     cabins
    -0.50
     expositions
    -0.48
     Pues
    -0.48
     zelve
    -0.48
     appartamento
    -0.47
     zoude
    -0.47
     serials
    -0.47
    POSITIVE LOGITS
     behalf
    0.76
     basis
    0.75
     occasion
    0.68
    ViewImports
    0.62
     occasions
    0.61
    reportWebVitals
    0.61
    RectangleBorder
    0.61
     дописавши
    0.59
     Réponses
    0.59
    twimg
    0.59
    Activations Density 3.242%

    No Known Activations