© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11007
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially Java and Swift code, including keywords like "module", "return", "package", "array", "list", and other terms related to software development.

    oai_token-act-pair · gemini-2.0-flash

    period

    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
     للاسماء
    -1.04
     صوتيه
    -1.02
    ValueStyle
    -0.92
    SharedDtor
    -0.91
    AndEndTag
    -0.90
    terness
    -0.89
    EDEFAULT
    -0.88
    intios
    -0.87
     protoimpl
    -0.85
    ErrUnexpectedEOF
    -0.85
    POSITIVE LOGITS
    .
    0.81
    [
    0.59
     [
    0.59
    。
    0.51
    ].
    0.50
    .[
    0.50
     [].
    0.48
    ".
    0.48
    ».
    0.47
     mukana
    0.46
    Activations Density 3.852%

    No Known Activations