© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13696
    Prev
    Next
    INDEX
    Explanations

    specifications for size, dimension, or quantity

    oai_token-act-pair · gemini-2.0-flash

    max/min

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    labus
    -0.68
     Мексичка
    -0.63
    fjspx
    -0.63
     CiNii
    -0.62
    rrggbb
    -0.61
    MessageOf
    -0.61
    ENODEV
    -0.60
     esternos
    -0.59
    OOTDTY
    -0.59
     néz
    -0.59
    POSITIVE LOGITS
    mern
    0.52
    mergeFrom
    0.48
     mer
    0.48
     we
    0.48
    下一篇
    0.46
     pas
    0.46
     suddenly
    0.46
    今
    0.46
    twimg
    0.46
     next
    0.45
    Activations Density 1.451%

    No Known Activations