© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12630
    Prev
    Next
    INDEX
    Explanations

    names, titles, and locations surrounded by punctuation

    oai_token-act-pair · gemini-2.0-flash

    commas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     Row
    -0.54
    ucht
    -0.54
    achable
    -0.53
    huriyet
    -0.50
    xFFFFFF
    -0.50
    DataColumn
    -0.50
     hObject
    -0.50
    relevant
    -0.49
    fsch
    -0.49
    helf
    -0.49
    POSITIVE LOGITS
     ujednoznacz
    0.69
     aged
    0.60
    الدراسه
    0.56
     age
    0.53
    View
    0.53
    Portail
    0.48
    AutoField
    0.47
     Bioaccumulative
    0.47
    Aged
    0.47
    gemar
    0.46
    Activations Density 1.532%

    No Known Activations