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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8343
    Prev
    Next
    INDEX
    Explanations

    words and phrases that occur inside scientific publications

    oai_token-act-pair · gemini-2.0-flash

    research papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    %}
    -0.58
    OGND
    -0.56
     jScrollPane
    -0.55
    المناصب
    -0.55
    '}>
    -0.54
    */;
    -0.53
     }}"></
    -0.52
    "](
    -0.52
    ;"></
    -0.51
    medriver
    -0.50
    POSITIVE LOGITS
     fréqu
    0.57
     ویکی‌آمباردا
    0.57
    GroupLayout
    0.53
     AppCompatTheme
    0.53
     Smoking
    0.53
     Losses
    0.53
     actionMode
    0.52
     Smo
    0.49
     fréquent
    0.48
     genotyping
    0.48
    Activations Density 5.563%

    No Known Activations