© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 5347
    Prev
    Next
    INDEX
    Explanations

    math notation and numbering

    oai_token-act-pair · gemini-2.0-flash

    technical writing

    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
     
    -1.88
    o
    -0.46
    "]="
    -0.42
    pausal
    -0.41
     FontWeight
    -0.40
     Bacchus
    -0.39
    IsInitialized
    -0.38
    )}_{
    -0.38
     medusa
    -0.38
    お
    -0.37
    POSITIVE LOGITS
    存于互联网档案馆
    0.73
     CURIAM
    0.71
     referrerpolicy
    0.69
    قایناقلار
    0.68
    SequentialGroup
    0.67
    twimg
    0.67
     CreateTagHelper
    0.63
    はじめに
    0.61
     المعيارى
    0.59
    ParallelGroup
    0.58
    Activations Density 7.805%

    No Known Activations