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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7311
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to scientific and political reports and writing

    oai_token-act-pair · gemini-2.0-flash

    complex technical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     كومونز
    -0.89
    TypedDataSet
    -0.74
    XmlAccessType
    -0.53
     насељу
    -0.52
    WebControls
    -0.51
     numberOfRows
    -0.51
     aDecoder
    -0.50
    انجليز
    -0.49
     sockaddr
    -0.48
     BoxFit
    -0.48
    POSITIVE LOGITS
    IUrlHelper
    0.58
    glTexCoord
    0.52
    ffering
    0.50
    umatic
    0.48
    Aggregator
    0.48
    ection
    0.48
    LogFactory
    0.47
     hospitalization
    0.47
    sient
    0.47
    CLUS
    0.46
    Activations Density 15.929%

    No Known Activations