© 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. 15742
    Prev
    Next
    INDEX
    Explanations

    words with unusual character combinations or formatting errors

    oai_token-act-pair · gemini-2.0-flash

    hyphen

    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
    -
    -0.57
    (
    -0.48
    بد
    -0.42
    wel
    -0.42
    {
    -0.41
    ce
    -0.38
    Ro
    -0.37
    .
    -0.37
    tran
    -0.37
    "
    -0.36
    POSITIVE LOGITS
    SequentialGroup
    1.06
    Personendaten
    0.98
     فريبيس
    0.96
    WebVitals
    0.96
    awtextra
    0.94
    UnusedPrivate
    0.94
    bootstrapcdn
    0.92
    NameInMap
    0.90
     وتسجيلات
    0.89
    InjectAttribute
    0.89
    Activations Density 2.024%

    No Known Activations