© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6996
    Prev
    Next
    INDEX
    Explanations

    phrases that present contrasting options or sides of an argument.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    uksessa
    -0.40
    break
    -0.36
    Lähteet
    -0.35
     бед
    -0.33
     entro
    -0.33
     break
    -0.32
    效
    -0.32
    ことになる
    -0.32
    runApp
    -0.32
    น์
    -0.31
    POSITIVE LOGITS
     one
    1.20
     starters
    1.16
    Firstly
    0.98
     Firstly
    0.95
     jednej
    0.86
     firstly
    0.85
     transférez
    0.85
    PreferredItem
    0.85
     Signalez
    0.83
    ंदीखरीदारी
    0.79
    Activations Density 0.827%

    No Known Activations