© 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. 3568
    Prev
    Next
    INDEX
    Explanations

    a wide variety of words and topics, seemingly with no coherent theme

    oai_token-act-pair · gemini-2.0-flash

    Hobbies and occupations

    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
    Geplaatst
    -0.92
    ValueStyle
    -0.71
     <>",
    -0.67
     незавершена
    -0.64
    XmlAccessType
    -0.63
    setVerticalGroup
    -0.63
     الحره
    -0.60
     ModelExpression
    -0.59
    ContentAsync
    -0.57
     مرئيه
    -0.54
    POSITIVE LOGITS
     virgin
    0.54
     vPvB
    0.52
    ervant
    0.50
    urman
    0.50
    carina
    0.49
     Paglinawan
    0.49
    virgin
    0.49
    Terminator
    0.49
    marvin
    0.49
    leyici
    0.48
    Activations Density 8.215%

    No Known Activations