© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5515
    Prev
    Next
    INDEX
    Explanations

    capitalized acronyms and chemicals, especially those starting with the letters "S", "C", or "P"

    oai_token-act-pair · gemini-2.0-flash

    Named entities

    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
     дописавши
    -0.62
    المناصب
    -0.57
    Diwedd
    -0.55
     Erişim
    -0.49
     فريبيس
    -0.47
     виправивши
    -0.46
     Tark
    -0.46
    theless
    -0.46
    مصادر
    -0.45
    ukai
    -0.45
    POSITIVE LOGITS
    vek
    0.57
    ISER
    0.56
    isin
    0.56
    NavigationView
    0.55
    이스
    0.53
    ViewData
    0.53
    antMatchers
    0.53
    IZ
    0.51
    IC
    0.50
    inerea
    0.50
    Activations Density 1.549%

    No Known Activations