© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12337
    Prev
    Next
    INDEX
    Explanations

    various parenthesis-like characters and some programming-specific terms

    oai_token-act-pair · gemini-2.0-flash

    parentheses

    np_max-act · 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
    はじめに
    -0.54
     незавершена
    -0.53
    netflix
    -0.52
    Televis
    -0.50
     tartalomajánló
    -0.49
    weds
    -0.48
     status
    -0.45
    Tikang
    -0.45
     TG
    -0.45
     Platt
    -0.45
    POSITIVE LOGITS
     חיצוניים
    0.61
    ooc
    0.57
    didReceive
    0.54
    Atsauces
    0.53
    NSIndexPath
    0.52
    mergeFrom
    0.50
     WaitForSeconds
    0.50
    AccessorTable
    0.49
    prepareStatement
    0.48
    nextProps
    0.48
    Activations Density 1.264%

    No Known Activations