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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 8438
    Prev
    Next
    INDEX
    Explanations

    words related to manufacturing, especially of metal parts

    oai_token-act-pair · gemini-2.0-flash

    Foreign 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
    Autoritní
    -0.77
     سكانية
    -0.75
    InjectAttribute
    -0.74
     ویکی‌پدی
    -0.74
     betweenstory
    -0.73
    tagHelperRunner
    -0.70
    Personendaten
    -0.68
    IndentedString
    -0.68
     lenker
    -0.68
     Audiodateien
    -0.68
    POSITIVE LOGITS
     ابت
    0.48
    Xoa
    0.48
     secco
    0.48
     equili
    0.47
     nổ
    0.46
     reacts
    0.46
    noticias
    0.44
    equili
    0.43
     lượng
    0.43
     cze
    0.42
    Activations Density 10.269%

    No Known Activations