© 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. 12883
    Prev
    Next
    INDEX
    Explanations

    words that are related to visual or studio or style or install

    oai_token-act-pair · gemini-2.0-flash

    visual

    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
     visual
    -2.56
     Visual
    -2.41
    Visual
    -2.33
    visual
    -2.25
     VISUAL
    -2.23
     visually
    -2.20
    VISUAL
    -1.91
     visuals
    -1.87
     visuelle
    -1.82
     visuel
    -1.70
    POSITIVE LOGITS
    DebuggerNonUser
    0.72
    GEBURTSDATUM
    0.68
    تقاوى
    0.64
     onOptions
    0.63
    Chham
    0.63
    脚注の使い方
    0.59
     MainAxisSize
    0.58
    RectangleBorder
    0.57
    BeginContext
    0.56
    BeginInit
    0.54
    Activations Density 3.312%

    No Known Activations