© 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. 12534
    Prev
    Next
    INDEX
    Explanations

    code snippets, as evidenced by the presence of brackets, variable assignments, and keywords like "length," "size," and "process"

    oai_token-act-pair · gemini-2.0-flash

    parentheses and semicolons

    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
    MetaType
    -0.59
    MemoryWarning
    -0.55
    XMLSchema
    -0.49
     ویکی‌آمباردا
    -0.48
     مشين
    -0.46
     Numerade
    -0.44
    件事情
    -0.44
    umbang
    -0.43
    tagext
    -0.43
    propTypes
    -0.43
    POSITIVE LOGITS
    InitVars
    0.55
     continúas
    0.52
     Normdatei
    0.52
    art
    0.51
    ^(@)
    0.50
    Népesség
    0.49
     Balan
    0.49
     truffle
    0.49
    hejiang
    0.49
    addCriterion
    0.49
    Activations Density 1.400%

    No Known Activations