© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5119
    Prev
    Next
    INDEX
    Explanations

    text related to scientific or research contexts

    oai_token-act-pair · gemini-2.0-flash

    b

    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
    fromnode
    -0.66
     مشين
    -0.59
    sizeCache
    -0.57
     indisponible
    -0.57
     يتيمه
    -0.55
    Rüyada
    -0.51
    IntoConstraints
    -0.50
    BagLayout
    -0.50
    Vidite
    -0.49
     EconPapers
    -0.48
    POSITIVE LOGITS
     b
    3.20
    b
    2.52
    ｂ
    1.56
     B
    1.45
     б
    1.44
     getB
    1.34
    B
    1.30
    getB
    1.29
    𝑏
    1.18
     ب
    1.14
    Activations Density 13.959%

    No Known Activations