© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2346
    Prev
    Next
    INDEX
    Explanations

    words that end in "ic" or contain "ile", especially if these words are related to medical, neuronal, or energetic processes.

    oai_token-act-pair · gemini-2.0-flash

    medical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    المناصب
    -0.77
     سكانية
    -0.61
    roughly
    -0.53
    وفاته
    -0.51
     roughly
    -0.51
    ธ์
    -0.48
    Cosmic
    -0.47
     potrivit
    -0.47
    الإنجليزية
    -0.46
     היתה
    -0.46
    POSITIVE LOGITS
    sizeCache
    0.77
    LLocation
    0.71
    XtraGrid
    0.65
     defaultstate
    0.64
     AssemblyCulture
    0.54
    slidesPer
    0.54
    }".
    0.53
     Domes
    0.52
     AssemblyVersion
    0.51
     pescoço
    0.50
    Activations Density 1.470%

    No Known Activations