© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8568
    Prev
    Next
    INDEX
    Explanations

    latex or math symbols

    oai_token-act-pair · gemini-2.0-flash

    Greek letters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     thats
    -1.26
    thats
    -1.09
     Thats
    -1.09
    Thats
    -1.02
     Efq
    -0.90
    That
    -0.88
     AssemblyTitle
    -0.88
    それも
    -0.88
     eso
    -0.87
     FetchType
    -0.85
    POSITIVE LOGITS
     v
    0.53
     fore
    0.51
     Lo
    0.51
     A
    0.50
     Y
    0.49
     V
    0.48
     av
    0.47
    {
    0.47
     d
    0.47
     C
    0.47
    Activations Density 3.543%

    No Known Activations