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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14584
    Prev
    Next
    INDEX
    Explanations

    phrases expressing the overall subjective assessment of something

    oai_token-act-pair · gemini-2.0-flash

    Reviews or discussions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     jScrollPane
    -0.73
    protoimpl
    -0.73
     חיצוניים
    -0.72
    OGND
    -0.71
    writeFieldEnd
    -0.67
    rungsseite
    -0.65
    aarrggbb
    -0.65
     propOrder
    -0.63
    IntoConstraints
    -0.61
     nonUne
    -0.61
    POSITIVE LOGITS
    ,{
    0.39
    격
    0.39
    oa̍t
    0.39
    يبة
    0.38
    ुल
    0.38
    goe
    0.37
     Leeuwen
    0.37
    /%
    0.37
    uler
    0.37
     sure
    0.37
    Activations Density 1.357%

    No Known Activations