© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8481
    Prev
    Next
    INDEX
    Explanations

    words relating to physical structures or engineering

    oai_token-act-pair · 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
    jsonwebtoken
    -0.50
     sap
    -0.44
    pada
    -0.40
    ulha
    -0.38
    colato
    -0.37
    fficio
    -0.37
    জ
    -0.37
     cumulative
    -0.37
    زار
    -0.36
     pada
    -0.36
    POSITIVE LOGITS
     structure
    1.20
     Structure
    1.19
    Structure
    1.17
    structure
    1.16
     STRUCTURE
    1.05
    yntaxException
    1.04
     structures
    1.04
     Struktur
    1.02
    structures
    1.01
    Struktur
    1.00
    Activations Density 1.161%

    No Known Activations