© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12903
    Prev
    Next
    INDEX
    Explanations

    phrases about death, including location, the age of death, and reference to a day, month or year

    oai_token-act-pair · gemini-2.0-flash

    Dates and 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_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     متعلقه
    -0.81
    ſelf
    -0.79
     ་་
    -0.79
    expandindo
    -0.76
     Réponses
    -0.73
    ſelves
    -0.73
     Majefty
    -0.72
     itſelf
    -0.71
     photolibrary
    -0.71
     greateſt
    -0.71
    POSITIVE LOGITS
     age
    0.63
    age
    0.47
     of
    0.47
     aged
    0.46
     at
    0.43
     for
    0.36
    he
    0.35
     from
    0.35
     flash
    0.35
    ALARM
    0.35
    Activations Density 0.933%

    No Known Activations