© 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. 5547
    Prev
    Next
    INDEX
    Explanations

    words related to research studies and scientific communication

    oai_token-act-pair · 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
    not
    -0.92
    always
    -0.91
    quite
    -0.91
    rather
    -0.87
     not
    -0.86
    simply
    -0.84
    still
    -0.83
    also
    -0.82
     always
    -0.82
    XmlAccessorType
    -0.82
    POSITIVE LOGITS
    ositol
    0.46
     mxArray
    0.46
     circulation
    0.41
    setupUi
    0.41
    ANTY
    0.40
    buttonShape
    0.40
     mocked
    0.40
     disambiguazione
    0.39
    dited
    0.39
    pana
    0.39
    Activations Density 8.975%

    No Known Activations