© 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. 6218
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to reading

    oai_token-act-pair · gemini-2.0-flash

    Reading books/articles

    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
     viewing
    -1.65
     Viewing
    -1.50
    viewing
    -1.45
    Viewing
    -1.41
     reading
    -1.30
     watching
    -1.28
     Reading
    -1.23
     viewer
    -1.23
     Watching
    -1.22
    reading
    -1.21
    POSITIVE LOGITS
    phosa
    0.58
     ModelExpression
    0.57
     Himo
    0.57
     تانيه
    0.50
    eddings
    0.50
     astore
    0.48
    WithIOException
    0.48
     старости
    0.47
    EndGlobalSection
    0.47
    новниш
    0.46
    Activations Density 1.543%

    No Known Activations