© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8799
    Prev
    Next
    INDEX
    Explanations

    numbers representing dates, particularly those including the digit 6 or 9

    oai_token-act-pair · gemini-2.0-flash

    Dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    Билгалдахарш
    -0.60
    #+#
    -0.56
    ölker
    -0.54
     greateſt
    -0.53
     AssemblyProduct
    -0.52
    Ansi
    -0.50
     nite
    -0.49
     EnglishChoose
    -0.49
    Filmografie
    -0.48
    mines
    -0.47
    POSITIVE LOGITS
    <bos>
    0.63
    ˈ
    0.63
     invokingState
    0.62
    phem
    0.60
    ябрь
    0.60
    quelize
    0.57
    PreExecute
    0.57
    rü
    0.56
     '\\;'
    0.54
    aarrggbb
    0.54
    Activations Density 0.226%

    No Known Activations