© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13962
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to shopping and making purchases

    oai_token-act-pair · gemini-2.0-flash

    Ad copy/software strings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     venuto
    -0.42
     potuto
    -0.37
    PACKET
    -0.37
     pioggia
    -0.37
     aquella
    -0.37
    io
    -0.36
    paž
    -0.35
     modernes
    -0.35
     strade
    -0.35
    M
    -0.34
    POSITIVE LOGITS
    setVerticalGroup
    1.19
     nahilalakip
    1.18
     autorytatywna
    1.15
    NameInMap
    1.11
    XmlAccessType
    1.10
    writeFieldEnd
    1.06
    CppMethod
    1.05
    UnusedPrivate
    1.01
    Geplaatst
    0.99
    ########.
    0.99
    Activations Density 0.913%

    No Known Activations