© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10644
    Prev
    Next
    INDEX
    Explanations

    French contractions starting with "qu'" or ending with "l'".

    oai_token-act-pair · gemini-2.0-flash

    apostrophe

    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
    تقاوى
    -0.63
    Revenir
    -0.62
    IntoConstraints
    -0.61
    存于互联网档案馆
    -0.58
    спонд
    -0.57
    ս
    -0.54
    figsize
    -0.53
     مشين
    -0.52
    ICEF
    -0.51
    bewerken
    -0.49
    POSITIVE LOGITS
     bahwa
    1.02
     that
    1.02
    <bos>
    0.84
     bahawa
    0.79
     ότι
    0.69
    that
    0.68
     dass
    0.68
     faptul
    0.65
     rằng
    0.64
     أنه
    0.63
    Activations Density 2.189%

    No Known Activations