© 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. 12621
    Prev
    Next
    INDEX
    Explanations

    country names and related adjectives, especially when discussing history or politics

    oai_token-act-pair · gemini-2.0-flash

    nationalities and origins

    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
    GEBURTSDATUM
    -0.80
     समीक्षाओं
    -0.75
     Germans
    -0.75
    AndEndTag
    -0.73
     Americans
    -0.71
     autorytatywna
    -0.70
     propOrder
    -0.69
     Italians
    -0.68
     CreateTagHelper
    -0.67
    AccessorTable
    -0.67
    POSITIVE LOGITS
    #+#
    0.47
    uci
    0.46
    藩
    0.42
    emi
    0.42
    طلحات
    0.42
     يونيو
    0.42
    testens
    0.42
    HtmlAttribute
    0.42
    topi
    0.41
    igshid
    0.41
    Activations Density 2.337%

    No Known Activations