© 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. 2246
    Prev
    Next
    INDEX
    Explanations

    legal documents with numeric references to time, laws, or legal actors

    oai_token-act-pair · gemini-2.0-flash

    units of time

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

    time durations

    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
     acorns
    -0.59
     raiſ
    -0.59
    GMENT
    -0.59
    Witam
    -0.59
     morire
    -0.58
     dieux
    -0.57
     fubject
    -0.57
     pleaſure
    -0.56
     Theſe
    -0.56
     esprits
    -0.55
    POSITIVE LOGITS
     years
    0.80
     months
    0.77
     weeks
    0.73
     year
    0.60
    findpost
    0.60
     Monate
    0.55
     años
    0.55
     YEARS
    0.54
     Years
    0.53
     yr
    0.53
    Activations Density 6.778%

    No Known Activations