© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6855
    Prev
    Next
    INDEX
    Explanations

    acronyms, abbreviations, and name suffixes often related to technology or people

    oai_token-act-pair · gemini-2.0-flash

    fx

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    ansing
    -0.55
    parsedMessage
    -0.54
    ldre
    -0.53
     sao
    -0.52
     '@
    -0.52
    fen
    -0.52
     blive
    -0.52
    rendon
    -0.52
    ).'
    -0.50
    ).$
    -0.50
    POSITIVE LOGITS
     تضيفلها
    0.68
     entanto
    0.60
    amaño
    0.57
    AsUp
    0.56
    idopsis
    0.56
    зулта
    0.54
     censiti
    0.53
    |()
    0.52
     дописавши
    0.51
    ViewInit
    0.50
    Activations Density 0.936%

    No Known Activations