© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13128
    Prev
    Next
    INDEX
    Explanations

    instances of the word "disappeared" and the past tense of the word "cause"

    oai_token-act-pair · gemini-2.0-flash

    disappeared

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ere
    -0.48
     copy
    -0.48
    asa
    -0.45
     Scala
    -0.45
     commission
    -0.44
    lich
    -0.44
     above
    -0.44
     Joss
    -0.44
     Marconi
    -0.44
     Erle
    -0.43
    POSITIVE LOGITS
    <bos>
    2.31
    GEBURTSDATUM
    1.04
     Савезне
    0.99
    脚注の使い方
    0.99
     autorytatywna
    0.92
     betweenstory
    0.90
    хьтан
    0.90
     '\\;'
    0.89
    InjectAttribute
    0.88
     Paglinawan
    0.87
    Activations Density 0.613%

    No Known Activations