© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5406
    Prev
    Next
    INDEX
    Explanations

    references to places, especially parks and trails in Illinois and/or with names that start with "K"

    oai_token-act-pair · gemini-2.0-flash

    Places in Illinois

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    tagHelperRunner
    -0.69
    MLLoader
    -0.66
    ########.
    -0.60
    Personendaten
    -0.59
    CrossRef
    -0.58
    findpost
    -0.57
     Normdatei
    -0.56
    Datuak
    -0.56
     autorytatywna
    -0.56
    WebServlet
    -0.55
    POSITIVE LOGITS
     Sampled
    0.47
     lõ
    0.47
     odası
    0.46
    frame
    0.46
     Arrived
    0.46
     یون
    0.46
     medallion
    0.46
     spied
    0.46
    >*/
    0.45
    IconModule
    0.45
    Activations Density 0.825%

    No Known Activations