© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6060
    Prev
    Next
    INDEX
    Explanations

    code snippets with numbers, code keywords, and formatting symbols

    oai_token-act-pair · gemini-2.0-flash

    Numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    SourceChecksum
    -0.66
    MigrationBuilder
    -0.60
    Билгалдахарш
    -0.59
    TagMode
    -0.59
     ostavi
    -0.57
     насељу
    -0.52
    Бахар
    -0.50
     EconPapers
    -0.49
    conf
    -0.47
    ye
    -0.47
    POSITIVE LOGITS
    ſelves
    0.67
     pleaſure
    0.63
    SBATCH
    0.62
     Majefty
    0.62
     defire
    0.62
     himſelf
    0.60
    ſelf
    0.60
     juſ
    0.59
     defStyleAttr
    0.59
     themſelves
    0.59
    Activations Density 3.641%

    No Known Activations