© 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. 13672
    Prev
    Next
    INDEX
    Explanations

    the string "type=text/javascript" in HTML or Javascript code

    oai_token-act-pair · gemini-2.0-flash

    /

    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
     ComVisible
    -0.67
    StoryboardSegue
    -0.62
    oredCriteria
    -0.59
    JspWriter
    -0.59
     Taktlose
    -0.54
     EconPapers
    -0.53
    Tazama
    -0.53
     HttpNotFound
    -0.51
    NameInMap
    -0.50
    UnsafeEnabled
    -0.50
    POSITIVE LOGITS
    :^{
    0.53
     AttributeSet
    0.49
    domen
    0.49
    imedes
    0.48
     bless
    0.47
    Text
    0.47
    <?,
    0.47
    arrings
    0.46
    xus
    0.46
    millan
    0.45
    Activations Density 0.412%

    No Known Activations