© 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. 12418
    Prev
    Next
    INDEX
    Explanations

    words related to publications/licensing and business organizations

    oai_token-act-pair · gemini-2.0-flash

    Legal and licensing

    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
     In
    -2.36
    In
    -2.14
     IN
    -1.79
     in
    -1.71
    getIn
    -1.35
    in
    -1.25
    NameIn
    -1.20
     в
    -1.14
     ใน
    -1.13
     în
    -1.13
    POSITIVE LOGITS
     Efq
    0.61
     mergeFrom
    0.59
    antaranya
    0.59
    :✨
    0.56
    addCriterion
    0.55
     Савезне
    0.55
    WebControls
    0.54
    numerusform
    0.52
    UnusedPrivate
    0.52
    graphicx
    0.52
    Activations Density 9.775%

    No Known Activations