© 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. 4779
    Prev
    Next
    INDEX
    Explanations

    information related to Indonesia, government officials and their statements.

    oai_token-act-pair · gemini-2.0-flash

    tokens related to conservation and environmental topics

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

    Indonesia, military, politics

    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
     nephe
    -0.51
     Medea
    -0.50
     thither
    -0.50
    errHandler
    -0.48
     Thine
    -0.47
    はじめに
    -0.47
     Ponto
    -0.47
     canst
    -0.46
     Oboe
    -0.46
     immortality
    -0.45
    POSITIVE LOGITS
    ècie
    0.71
    choly
    0.71
    verwijspagina
    0.67
    lccn
    0.60
    stateMutability
    0.60
    省市镇
    0.59
     rhestr
    0.57
    webElementXpaths
    0.57
    igny
    0.56
     Wicidata
    0.54
    Activations Density 0.323%

    No Known Activations