© 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. 15966
    Prev
    Next
    INDEX
    Explanations

    code in various programming and markup languages including XML

    oai_token-act-pair · gemini-2.0-flash

    forms of "of"

    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
     Efq
    -0.88
     Monfieur
    -0.73
     Anſ
    -0.73
    Datuak
    -0.72
     whoſe
    -0.66
     myſelf
    -0.60
     Eſ
    -0.60
     asunder
    -0.59
    ſelf
    -0.56
     مرئيه
    -0.56
    POSITIVE LOGITS
     del
    1.57
     della
    1.51
     ofthe
    1.43
    ofthe
    1.41
    OfThe
    1.34
     des
    1.27
     dell
    1.27
     delle
    1.26
     degli
    1.10
     dels
    1.09
    Activations Density 0.936%

    No Known Activations