© 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. 4521
    Prev
    Next
    INDEX
    Explanations

    words related to scientific materials

    oai_token-act-pair · gemini-2.0-flash

    scientific/technical processes

    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
    NameInMap
    -0.73
     CreateTagHelper
    -0.70
     kasarigan
    -0.68
    CppMethod
    -0.68
    TypedDataSet
    -0.63
    :✨
    -0.63
     Италијани
    -0.63
     otomatig
    -0.61
    PYX
    -0.61
     становника
    -0.60
    POSITIVE LOGITS
    '
    0.74
    ’
    0.68
     InputDecoration
    0.54
     való
    0.49
     retreating
    0.46
     resisting
    0.45
     withdrawing
    0.45
     BoxDecoration
    0.45
     subtracting
    0.45
     perdiendo
    0.45
    Activations Density 14.352%

    No Known Activations