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. 8-GEMMASCOPE-TRANSCODER-16K
    4. 1160
    Prev
    Next
    INDEX
    Explanations

    words and phrases that describe things happening too soon

    oai_token-act-pair · gemini-2.0-flash

    early

    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
     TextAppearance
    -0.77
     препратки
    -0.76
    PerformLayout
    -0.73
    KommentareTeilen
    -0.71
    Portály
    -0.70
    oa̍t
    -0.70
    хьтан
    -0.67
    #+#
    -0.66
     InputDecoration
    -0.65
    مقاله
    -0.65
    POSITIVE LOGITS
     adelant
    0.47
    ToBounds
    0.46
     anticipo
    0.43
    早
    0.43
    ppen
    0.41
     dini
    0.38
    我先
    0.38
     anul
    0.38
    Act
    0.38
     advance
    0.38
    Activations Density 1.273%

    No Known Activations