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. 4-GEMMASCOPE-TRANSCODER-16K
    4. 7708
    Prev
    Next
    INDEX
    Explanations

    snippets of conversations in languages other than English, especially French and Portugese, and it also seems to activate on lists of options.

    oai_token-act-pair · gemini-2.0-flash

    French

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     et
    -0.70
    <bos>
    -0.68
     ou
    -0.59
     e
    -0.57
     o
    -0.56
     s
    -0.56
     u
    -0.55
    ItemLayout
    -0.54
     d
    -0.54
     a
    -0.53
    POSITIVE LOGITS
     purpoſe
    1.07
     myſelf
    1.01
     ſeveral
    0.99
     reaſon
    0.98
     greateſt
    0.96
     Monfieur
    0.96
     themſelves
    0.94
     pleaſure
    0.94
     Majefty
    0.93
     diſt
    0.90
    Activations Density 7.132%

    No Known Activations