© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12728
    Prev
    Next
    INDEX
    Explanations

    various web development code snippets and tags, along with code repository links

    oai_token-act-pair · gemini-2.0-flash

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     end
    -0.57
     touch
    -0.47
     sum
    -0.47
     on
    -0.43
     department
    -0.43
     Sun
    -0.43
     speak
    -0.43
     mix
    -0.42
     is
    -0.41
     express
    -0.41
    POSITIVE LOGITS
     nahilalakip
    1.29
     CreateTagHelper
    1.27
    UnusedPrivate
    1.26
    ⓧ
    1.16
    IsContent
    1.15
     pinulongan
    1.14
     Roskov
    1.12
    verwijspagina
    1.08
     autorytatywna
    1.07
    存于互联网档案馆
    1.06
    Activations Density 21.659%

    No Known Activations