© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6480
    Prev
    Next
    INDEX
    Explanations

    mentions of feminism and date formats

    oai_token-act-pair · gemini-2.0-flash

    dates and time

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     تضيفلها
    -0.69
     nakalista
    -0.63
    ьаж
    -0.62
    ьажоргаш
    -0.58
     CURIAM
    -0.53
     Weekly
    -0.52
    mappedBy
    -0.52
    zwi
    -0.52
    KommentareTeilen
    -0.52
     gram
    -0.52
    POSITIVE LOGITS
     era
    1.16
     decade
    1.09
     period
    1.05
     década
    1.05
     dates
    1.04
     date
    1.03
     years
    0.97
     Era
    0.97
     époque
    0.97
     eras
    0.97
    Activations Density 4.823%

    No Known Activations