© 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. 14795
    Prev
    Next
    INDEX
    Explanations

    mentions of quantities of years

    oai_token-act-pair · gemini-2.0-flash

    years of experience

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

    say "years"

    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
     Wicidata
    -0.56
    ByPrimaryKey
    -0.50
     Dec
    -0.49
     Raton
    -0.48
    hésite
    -0.47
     DEC
    -0.46
    Dieter
    -0.45
    iov
    -0.44
    Искәрмәләр
    -0.44
     virkelig
    -0.44
    POSITIVE LOGITS
     year
    0.93
     years
    0.79
     YEAR
    0.75
    year
    0.75
    Year
    0.73
     Years
    0.70
     Year
    0.69
    +#+#
    0.69
     semesters
    0.68
    ########.
    0.68
    Activations Density 1.225%

    No Known Activations