© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5091
    Prev
    Next
    INDEX
    Explanations

    phrases discussing accountability and legal contexts

    oai_token-act-pair · gemini-2.0-flash

    prepositions indicating location or association

    np_token-act-pair-logits · gpt-4o-mini

    responsibility

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    windowFixed
    -0.79
    endphp
    -0.73
    AddTagHelper
    -0.68
    tableFuture
    -0.62
    contentLoaded
    -0.61
     surla
    -0.61
     مشين
    -0.60
     يتيمه
    -0.60
    abestanden
    -0.60
    hematics
    -0.59
    POSITIVE LOGITS
     chez
    1.18
     with
    1.08
     bei
    1.06
     beim
    0.98
     auprès
    0.93
     bij
    0.82
     conosco
    0.79
     comigo
    0.77
     với
    0.77
     نزد
    0.77
    Activations Density 2.364%

    No Known Activations