© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6267
    Prev
    Next
    INDEX
    Explanations

    linking/transition words that connect ideas or arguments.

    oai_token-act-pair · gemini-2.0-flash

    numbers

    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
    SequentialGroup
    -0.69
    HtmlAttribute
    -0.69
     Winaray
    -0.65
    Искәрмәләр
    -0.56
    addGap
    -0.56
    География
    -0.55
    SPATH
    -0.53
     Outro
    -0.51
    instancetype
    -0.50
    öglichkeiten
    -0.49
    POSITIVE LOGITS
     four
    2.48
     five
    2.34
     six
    2.25
     three
    2.20
     seven
    2.16
     eight
    2.06
    four
    2.03
     nine
    2.00
    five
    1.88
    three
    1.84
    Activations Density 4.394%

    No Known Activations