© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11824
    Prev
    Next
    INDEX
    Explanations

    the year

    oai_token-act-pair · gemini-2.0-flash

    non-English or foreign language tokens

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

    Legal filings with dates

    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
    our
    -0.68
    urer
    -0.65
    orship
    -0.60
    ors
    -0.59
    orde
    -0.57
    oris
    -0.57
    org
    -0.57
    örer
    -0.57
    ore
    -0.56
    orem
    -0.55
    POSITIVE LOGITS
     للاسماء
    0.64
    іга
    0.57
    momix
    0.57
    észetes
    0.54
     تضيفلها
    0.54
    entier
    0.52
    </tfoot>
    0.52
    rungsseite
    0.50
    bonucle
    0.50
    Quanto
    0.50
    Activations Density 0.606%

    No Known Activations