© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7166
    Prev
    Next
    INDEX
    Explanations

    mentions of building materials, especially stone and brick, and related terms.

    oai_token-act-pair · gemini-2.0-flash

    bricks and stones

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Normdatei
    -0.62
    kuuta
    -0.56
    HandlerContext
    -0.52
    醐
    -0.52
     Suf
    -0.51
     sumpay
    -0.50
    mobileqq
    -0.50
     Dí
    -0.50
    eam
    -0.50
    osoba
    -0.50
    POSITIVE LOGITS
     stone
    1.04
     stones
    0.93
     Stone
    0.88
     STONE
    0.82
    Stone
    0.82
    stone
    0.79
     paving
    0.78
     pave
    0.74
     bricks
    0.73
     Stones
    0.73
    Activations Density 0.503%

    No Known Activations