© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12025
    Prev
    Next
    INDEX
    Explanations

    the word "with" and words sometimes found nearby

    oai_token-act-pair · gemini-2.0-flash

    with/without

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    abetes
    -0.85
    AnimationsModule
    -0.71
     facie
    -0.70
    ември
    -0.68
    ViewFeatures
    -0.65
     تضيفلها
    -0.65
     eventdata
    -0.65
    enumi
    -0.64
     CHAPITRE
    -0.63
    Datuak
    -0.62
    POSITIVE LOGITS
    vesti
    0.46
    stadt
    0.45
     And
    0.45
    hias
    0.45
     s
    0.45
     Mr
    0.45
    check
    0.44
    WireFormatLite
    0.44
    veste
    0.42
    вина
    0.42
    Activations Density 0.352%

    No Known Activations