© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6764
    Prev
    Next
    INDEX
    Explanations

    a possible racist coding given the context, or terms ending in "ck," "té", words "side" and "of". Also, finds words related to geography

    oai_token-act-pair · gemini-2.0-flash

    latex code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     resourceCulture
    -0.50
    getManager
    -0.50
    okai
    -0.47
    transQ
    -0.45
    bigcap
    -0.44
     الرياضيه
    -0.43
     caccia
    -0.42
     biens
    -0.42
     gea
    -0.41
    îtra
    -0.41
    POSITIVE LOGITS
     side
    1.95
     SIDE
    1.72
    Side
    1.72
     Side
    1.70
     sides
    1.58
    side
    1.57
    SIDE
    1.48
     Sides
    1.26
    sides
    1.25
    Sides
    1.23
    Activations Density 0.601%

    No Known Activations