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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13744
    Prev
    Next
    INDEX
    Explanations

    a mix of Japanese sentence ending forms, URLs, code snippets, and error messages.

    oai_token-act-pair · gemini-2.0-flash

    code and error messages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    клопе
    -0.70
     مرئيه
    -0.54
    qxd
    -0.54
     Wicidata
    -0.52
     himo
    -0.51
     Vikipedi
    -0.50
    ائي
    -0.49
    érat
    -0.48
    PhysRevD
    -0.47
    cedure
    -0.47
    POSITIVE LOGITS
     OFDb
    0.59
     and
    0.57
     الحره
    0.57
    MessageOf
    0.54
    ########.
    0.53
    čkou
    0.51
    IntoConstraints
    0.51
    DeleteBehavior
    0.50
     وتسجيلات
    0.50
    发表于
    0.49
    Activations Density 1.849%

    No Known Activations