© 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. 14139
    Prev
    Next
    INDEX
    Explanations

    language related to passage of time, especially years

    oai_token-act-pair · gemini-2.0-flash

    terms related to celebrations and milestones

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

    Time duration/span

    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
     Eighteenth
    -0.56
     Fifteen
    -0.54
     Thirteenth
    -0.54
     seventeenth
    -0.53
     Seventeenth
    -0.52
     nineteenth
    -0.51
     Tenth
    -0.50
     Nineteenth
    -0.50
    Clik
    -0.50
     &___
    -0.50
    POSITIVE LOGITS
     виправивши
    0.67
    queryInterface
    0.67
     мәкал
    0.64
    tvguidetime
    0.58
    OfBirth
    0.58
     roulant
    0.56
    ürtel
    0.52
    manni
    0.52
    selas
    0.52
     myſelf
    0.52
    Activations Density 2.465%

    No Known Activations