© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10637
    Prev
    Next
    INDEX
    Explanations

    conjunctions with adjacent words that indicate a contrast is being made or an opinion is being shared.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     betweenstory
    -0.80
     Италијани
    -0.75
     onOptions
    -0.72
     ویکی‌پدی
    -0.72
    IonicModule
    -0.71
    deelte
    -0.71
     للمعارف
    -0.70
     كمان
    -0.68
     Baillargeon
    -0.65
     Bourgoin
    -0.65
    POSITIVE LOGITS
    |}{
    0.50
    #+#
    0.48
     entier
    0.48
     par
    0.47
    awaiter
    0.46
    ye
    0.45
    par
    0.44
     PAR
    0.44
     xmlns
    0.43
    Revenir
    0.42
    Activations Density 0.635%

    No Known Activations