© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10390
    Prev
    Next
    INDEX
    Explanations

    a variety of formatting elements, as well as some language tags and years.

    oai_token-act-pair · 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
    BeginContext
    -0.79
    TagMode
    -0.77
     Theſe
    -0.69
     يتيمه
    -0.68
     Efq
    -0.67
     صوتيه
    -0.66
    }$​
    -0.64
    styleType
    -0.63
     مرئيه
    -0.62
     ویکی‌پدیا
    -0.62
    POSITIVE LOGITS
     démocr
    0.62
     fraî
    0.59
     américains
    0.57
     fermés
    0.57
     garçons
    0.56
     courants
    0.56
     malades
    0.54
     africains
    0.54
     sanitaires
    0.54
     rempliss
    0.53
    Activations Density 1.858%

    No Known Activations