© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 7732
    Prev
    Next
    INDEX
    Explanations

    section headers or the beginning of a quotation in multiple languages.

    oai_token-act-pair · gemini-2.0-flash

    Stop words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     cauſe
    -0.71
     the
    -0.70
     purpoſe
    -0.69
     existence
    -0.68
     reaſon
    -0.66
     Theſe
    -0.65
     ſeveral
    -0.62
     Monfieur
    -0.61
     ſtate
    -0.60
     itſelf
    -0.60
    POSITIVE LOGITS
    Datuak
    0.63
     Meksiku
    0.60
    Бахар
    0.59
    queryInterface
    0.56
     Biôgrafia
    0.53
    Personensuche
    0.52
    adpleegd
    0.52
     ویکی‌پدی
    0.52
     alá
    0.52
    Nazionale
    0.52
    Activations Density 0.686%

    No Known Activations