© 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. 5764
    Prev
    Next
    INDEX
    Explanations

    uses of dot notation in coding contexts

    oai_token-act-pair · gemini-2.0-flash

    say "code appending"

    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
    invokeLater
    -0.82
     oprot
    -0.80
     gyhoeddwyd
    -0.76
    ChildScrollView
    -0.74
     Exacts
    -0.74
    !("{}",
    -0.71
    ReusableCell
    -0.71
    chowa
    -0.70
    tagext
    -0.70
    addPreferredGap
    -0.69
    POSITIVE LOGITS
    chl
    0.44
     suspe
    0.44
     fédé
    0.42
     متعلقه
    0.41
     letti
    0.40
    外部リンク
    0.40
     esquer
    0.39
    append
    0.38
    net
    0.36
    dana
    0.36
    Activations Density 0.396%

    No Known Activations