© 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. 11200
    Prev
    Next
    INDEX
    Explanations

    clauses starting with "if"

    oai_token-act-pair · gemini-2.0-flash

    if

    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
    subsubsection
    -0.49
    wapV
    -0.45
    ichio
    -0.43
    UBLE
    -0.42
    Consequences
    -0.42
     Corbin
    -0.41
    mentable
    -0.41
     gallo
    -0.41
     становника
    -0.41
    chien
    -0.41
    POSITIVE LOGITS
     ModelExpression
    0.66
    basicConfig
    0.65
     unknownFields
    0.59
     насељу
    0.58
    __((
    0.58
     ostavi
    0.58
    MLLoader
    0.57
    HasForeignKey
    0.57
    الإنجليزية
    0.57
    lalu
    0.56
    Activations Density 0.286%

    No Known Activations