© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7248
    Prev
    Next
    INDEX
    Explanations

    text discussing a past memory of Lego toys

    oai_token-act-pair · gemini-2.0-flash

    Lego bricks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     brick
    -1.74
    brick
    -1.71
     Brick
    -1.70
    Brick
    -1.70
     Bricks
    -1.52
     bricks
    -1.50
    bricks
    -1.45
     cement
    -1.42
     concrete
    -1.38
     Clay
    -1.38
    POSITIVE LOGITS
     Mal
    0.47
     Melch
    0.45
     Seymour
    0.44
     Jungfrau
    0.43
    mobileqq
    0.43
    mal
    0.42
    Mal
    0.42
    Sainte
    0.41
    nter
    0.41
     MTB
    0.41
    Activations Density 1.085%

    No Known Activations