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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12108
    Prev
    Next
    INDEX
    Explanations

    code and data, especially pertaining to file processing and specific data labels

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    StructEnd
    -0.72
    espół
    -0.59
    aarrggbb
    -0.58
    mybatisplus
    -0.58
     Мексичка
    -0.57
     Signalez
    -0.57
    bootstrapcdn
    -0.57
    BufferException
    -0.55
    NewUrlParser
    -0.52
     ویکی‌پدیای
    -0.52
    POSITIVE LOGITS
    руса
    0.50
    OLOGIE
    0.49
    ⇑
    0.49
    存于互联网档案馆
    0.48
    politan
    0.46
     wy
    0.44
    ❋
    0.44
    RegistryLite
    0.44
    wir
    0.43
    usa
    0.43
    Activations Density 7.010%

    No Known Activations