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. 879
    Prev
    Next
    INDEX
    Explanations

    a mix of disease words, code snippets, and version numbers.

    oai_token-act-pair · gemini-2.0-flash

    scientific/technical text

    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
     nakalista
    -0.80
    DockStyle
    -0.56
    $_['
    -0.54
    thâu
    -0.53
    MergeFrom
    -0.52
    (!__
    -0.51
     Lokales
    -0.50
    ьаж
    -0.50
    rinfo
    -0.50
    extField
    -0.49
    POSITIVE LOGITS
     hunne
    0.58
    HomeAsUpEnabled
    0.57
     peindre
    0.53
     NDEBUG
    0.52
     Monfieur
    0.51
     skolen
    0.50
     ellers
    0.50
     durumda
    0.50
     résult
    0.50
     zelve
    0.49
    Activations Density 3.718%

    No Known Activations