© 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
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 13137
    Prev
    Next
    INDEX
    Explanations

    text that is the beginning of a structured section of a document, like a title, subtitle or numbered list

    oai_token-act-pair · gemini-2.0-flash

    invention descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    ↵↵
    -1.00
     D
    -0.66
     B
    -0.66
     
    -0.66
     H
    -0.60
     I
    -0.60
     "
    -0.59
    ")){
    
    -0.59
     C
    -0.59
     M
    -0.58
    POSITIVE LOGITS
     itſelf
    0.90
     Shakspeare
    0.88
     ་་
    0.83
     photolibrary
    0.80
     mohair
    0.78
     himſelf
    0.78
     ovp
    0.76
     Shaksp
    0.76
    ſelves
    0.74
    Probably
    0.74
    Activations Density 0.881%

    No Known Activations