Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 16-GEMMASCOPE-TRANSCODER-16K
    4. 1102
    Prev
    Next
    INDEX
    Explanations

    references to the visual arts and film, as well statements of expertise

    oai_token-act-pair · gemini-2.0-flash

    technical jargon

    np_token-act-pair-logits · gemini-2.0-flash

    About me description

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.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
    expandindo
    -0.87
    mybatisplus
    -0.81
    出版年
    -0.79
     endwhile
    -0.79
    ="@+
    -0.79
    }}],
    -0.74
     فريبيس
    -0.72
    ]--;
    -0.71
     Audiodateien
    -0.69
     ivelany
    -0.68
    POSITIVE LOGITS
    ísima
    0.41
     {}
    0.41
     Inc
    0.41
    UserController
    0.40
    ne
    0.40
    /**
    0.39
     pieces
    0.39
     top
    0.38
     StatelessWidget
    0.38
    塑
    0.38
    Activations Density 2.034%

    No Known Activations