© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10870
    Prev
    Next
    INDEX
    Explanations

    locations in Northern Ireland, especially in County Antrim, and also some numbers associated with dates or populations.

    oai_token-act-pair · gemini-2.0-flash

    Northern Ireland

    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
    Not in Any Lists

    No Comments

    Negative Logits
    British
    -0.52
    egrave
    -0.51
     BRITISH
    -0.49
     British
    -0.49
    🏼
    -0.48
    cinas
    -0.47
    hagic
    -0.47
    british
    -0.47
    🏽
    -0.46
    removeAttribute
    -0.44
    POSITIVE LOGITS
    providedIn
    0.78
    styleType
    0.76
    LEncoder
    0.71
     nahilalakip
    0.71
    StructEnd
    0.71
    LookAnd
    0.70
    MigrationBuilder
    0.70
     Roskov
    0.68
    IntoConstraints
    0.68
    ThroughAttribute
    0.67
    Activations Density 1.614%

    No Known Activations