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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8278
    Prev
    Next
    INDEX
    Explanations

    words related to royal leaders and geopolitical topics related to Denmark and Germany

    oai_token-act-pair · gemini-2.0-flash

    specific proper nouns or formal titles

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

    Titles

    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
    WebVitals
    -0.59
     allé
    -0.58
     OFDb
    -0.52
    WebControls
    -0.52
     annular
    -0.51
     meleg
    -0.50
    EndTag
    -0.49
    palette
    -0.49
     peaking
    -0.49
     architectural
    -0.48
    POSITIVE LOGITS
     AssemblyCompany
    0.62
     propOrder
    0.58
    Джерела
    0.49
    RTRS
    0.46
    ########.
    0.46
    스템
    0.44
     محفوظة
    0.44
     infatti
    0.44
     Cristi
    0.44
    ricted
    0.44
    Activations Density 1.638%

    No Known Activations