© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11899
    Prev
    Next
    INDEX
    Explanations

    HTML input tags and the term "change" after "on"

    oai_token-act-pair · gemini-2.0-flash

    input

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    input
    -1.26
     input
    -0.84
    Input
    -0.79
    INPUT
    -0.78
     INPUT
    -0.70
     Input
    -0.69
    输入
    -0.68
    AsUp
    -0.67
    engagent
    -0.63
    )");
    -0.63
    POSITIVE LOGITS
    AccessorTable
    0.68
    AndEndTag
    0.65
     snippetHide
    0.60
    AlterField
    0.50
    outer
    0.50
     newest
    0.48
     månader
    0.47
    Instru
    0.47
    Raising
    0.47
     ngược
    0.46
    Activations Density 0.422%

    No Known Activations