© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11134
    Prev
    Next
    INDEX
    Explanations

    various different kinds of formatting and references in text

    oai_token-act-pair · gemini-2.0-flash

    scientific/technical texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     jScrollPane
    -0.84
     Klon
    -0.71
     Juf
    -0.67
    XmlAccessType
    -0.66
    Tembelea
    -0.63
     demografica
    -0.60
     Kalis
    -0.59
    EndProject
    -0.59
     JAXBElement
    -0.59
     Judas
    -0.59
    POSITIVE LOGITS
     commerciaux
    0.69
     supérieurs
    0.63
     sauvages
    0.62
     religieuses
    0.60
     démocr
    0.60
     commerciales
    0.59
     humains
    0.59
     extérieurs
    0.58
     morts
    0.54
     africains
    0.54
    Activations Density 1.467%

    No Known Activations