© 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. 11600
    Prev
    Next
    INDEX
    Explanations

    the word "surface".

    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
     surface
    -2.88
     Surface
    -2.83
    Surface
    -2.72
    surface
    -2.64
     SURFACE
    -2.61
     surfaces
    -2.39
    SURFACE
    -2.31
     Surfaces
    -2.25
    surfaces
    -2.05
    urface
    -1.95
    POSITIVE LOGITS
    errHandler
    0.68
    FormTagHelper
    0.59
    ArrowToggle
    0.58
    はじめに
    0.58
     onCancelled
    0.55
    WriteBarrier
    0.55
     protoimpl
    0.54
    MemoryWarning
    0.53
    éez
    0.52
    XtraReports
    0.52
    Activations Density 3.048%

    No Known Activations