© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7681
    Prev
    Next
    INDEX
    Explanations

    ages expressed numerically including the word "year"

    oai_token-act-pair · gemini-2.0-flash

    the concept of "year"

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

    ages

    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
    Personensuche
    -0.67
    transQ
    -0.65
    colgroup
    -0.64
    complexType
    -0.62
    mitian
    -0.57
     ब्रेकडाउन
    -0.57
     parseFrom
    -0.57
     Reverso
    -0.57
    RefNanny
    -0.56
    multicolumn
    -0.55
    POSITIVE LOGITS
     year
    1.13
    year
    0.87
    Year
    0.82
     Year
    0.82
     years
    0.79
     YEAR
    0.75
     année
    0.74
     tahun
    0.73
     Years
    0.70
    YEAR
    0.69
    Activations Density 1.224%

    No Known Activations