© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4190
    Prev
    Next
    INDEX
    Explanations

    technical and scientific terms, especially those related to nanotechnology and chemistry.

    oai_token-act-pair · gemini-2.0-flash

    nanotechnology

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    protoimpl
    -0.42
    ISTRO
    -0.42
     enx
    -0.40
    CJK
    -0.38
     Yarm
    -0.37
    IANGLES
    -0.37
    XmlType
    -0.37
    íncipe
    -0.36
    irmish
    -0.36
    HEAST
    -0.36
    POSITIVE LOGITS
    o
    0.97
    os
    0.90
    ot
    0.89
    oj
    0.88
    oc
    0.88
    ol
    0.85
    OF
    0.85
    о
    0.84
    otu
    0.84
    ｏ
    0.84
    Activations Density 9.606%

    No Known Activations