© 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. 1493
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to political protest, policing, imprisonment, and violence, particularly in the context of specific place names and organizations.

    oai_token-act-pair · gemini-2.0-flash

    Swaziland

    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
    Obras
    -0.55
    ]--;
    -0.54
     onOptions
    -0.53
    Personendaten
    -0.53
    ècie
    -0.50
    TagMode
    -0.48
    specie
    -0.48
    ⁡
    -0.48
    OOTDTY
    -0.47
    Traceback
    -0.47
    POSITIVE LOGITS
    expandindo
    0.61
     ویکی‌پدی
    0.57
    vaadin
    0.56
    Portale
    0.51
     Wikiseite
    0.49
    LookAnd
    0.47
     imp
    0.46
     PPM
    0.45
    DataLoader
    0.45
     ман
    0.43
    Activations Density 14.530%

    No Known Activations