© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 67
    Prev
    Next
    INDEX
    Explanations

    code related to kotlin files in "io.gitlab.arturbosch.detekt"

    oai_token-act-pair · gemini-2.0-flash

    dete

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    <bos>
    -0.58
     tearDown
    -0.49
     shield
    -0.49
     mark
    -0.44
     she
    -0.44
     net
    -0.44
     miss
    -0.44
    CGI
    -0.42
     gun
    -0.42
     Mav
    -0.42
    POSITIVE LOGITS
     <=",
    0.87
    AndEndTag
    0.81
     lenker
    0.62
     bağlantılar
    0.60
     propOrder
    0.58
     vulgaires
    0.58
    {#
    0.57
    出版年
    0.56
    urten
    0.54
     poros
    0.52
    Activations Density 42.170%

    No Known Activations