© 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. 12465
    Prev
    Next
    INDEX
    Explanations

    Java code containing periods and numbers

    oai_token-act-pair · 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
     bugged
    -0.46
     inves
    -0.44
     Advance
    -0.44
    mittag
    -0.43
     advance
    -0.43
     step
    -0.43
    Produzione
    -0.42
    Termine
    -0.42
     crash
    -0.42
    dist
    -0.41
    POSITIVE LOGITS
    出版年
    0.82
    RegressionTest
    0.71
    Ārējās
    0.63
    حياته
    0.57
    MENAFN
    0.57
     يتيمه
    0.57
    ngdoc
    0.57
    matchCondition
    0.56
    Tē
    0.56
     désolés
    0.56
    Activations Density 0.194%

    No Known Activations