© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7161
    Prev
    Next
    INDEX
    Explanations

    content that refers to Sri Lanka

    oai_token-act-pair · gemini-2.0-flash

    Sri

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ########.
    -0.92
    adpleegd
    -0.69
     Bourgoin
    -0.69
    WireFormatLite
    -0.68
     مشين
    -0.68
     useStyles
    -0.66
     محفوظة
    -0.65
    astify
    -0.65
    Насе
    -0.64
    thâu
    -0.63
    POSITIVE LOGITS
     sitten
    0.47
    FormTagHelper
    0.47
     Bernhard
    0.45
     rurale
    0.43
    reactstrap
    0.42
    bisoft
    0.40
    
    0.38
     поле
    0.37
     pada
    0.37
    lan
    0.37
    Activations Density 0.474%

    No Known Activations