© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12196
    Prev
    Next
    INDEX
    Explanations

    dates, especially those in December

    oai_token-act-pair · gemini-2.0-flash

    numerical dates and related patterns

    np_token-act-pair-logits · gpt-4o-mini

    0

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    ⓧ
    -0.97
    SharedDtor
    -0.96
     متعلقه
    -0.92
    Filmographie
    -0.90
    mybatisplus
    -0.85
     EconPapers
    -0.83
    IndentedString
    -0.83
    帖最后由
    -0.83
     Paglinawan
    -0.82
    ++];
    -0.81
    POSITIVE LOGITS
    1
    0.60
     pr
    0.48
     t
    0.47
    ga
    0.46
     n
    0.45
    터
    0.45
    po
    0.45
     gi
    0.44
    2
    0.44
     p
    0.43
    Activations Density 1.329%

    No Known Activations