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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11383
    Prev
    Next
    INDEX
    Explanations

    words related to legal proceedings and government

    oai_token-act-pair · gemini-2.0-flash

    words related to inquiries or questions

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

    that

    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
    aarrggbb
    -0.65
    ाहरण
    -0.63
     виправивши
    -0.61
     kasarigan
    -0.59
    expandindo
    -0.59
     rằng
    -0.58
    antMatchers
    -0.58
    Tembelea
    -0.58
    Демографія
    -0.57
     bahwa
    -0.56
    POSITIVE LOGITS
     which
    2.95
    which
    2.44
     Which
    2.23
    Which
    2.14
     WHICH
    2.09
    hich
    1.62
     laquelle
    1.41
     οποία
    1.39
     quale
    1.38
     cual
    1.38
    Activations Density 11.745%

    No Known Activations