© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13886
    Prev
    Next
    INDEX
    Explanations

    mentions of financial transactions, formal complaints, license agreements, or political campaigns

    oai_token-act-pair · gemini-2.0-flash

    formal writing snippets

    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
     Bourgoin
    -0.56
     الرياضيه
    -0.46
     فريبيس
    -0.45
    complexContent
    -0.44
    AnimationsModule
    -0.44
     dirigez
    -0.44
    isDebugEnabled
    -0.43
    HandlerContext
    -0.40
    endpush
    -0.40
    [++
    -0.40
    POSITIVE LOGITS
     c
    0.72
    webElementXpaths
    0.62
    期刊论文
    0.58
    BASEPATH
    0.58
     ci
    0.58
    autogui
    0.57
     Chemical
    0.56
     Carpenter
    0.56
     Transport
    0.55
    Transport
    0.55
    Activations Density 10.260%

    No Known Activations