© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6607
    Prev
    Next
    INDEX
    Explanations

    text related to recycling different materials and the word "for."

    oai_token-act-pair · gemini-2.0-flash

    plastic

    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
    migrationBuilder
    -0.73
    Datuak
    -0.61
     referrerpolicy
    -0.58
     SDLK
    -0.57
     initComponents
    -0.56
     mapStateToProps
    -0.54
    contentLoaded
    -0.53
     JpaRepository
    -0.53
     réunis
    -0.51
     División
    -0.50
    POSITIVE LOGITS
     CreateTagHelper
    0.65
    OGND
    0.56
    abes
    0.47
    黙
    0.46
     leksikon
    0.46
    frequencies
    0.45
    zehnten
    0.44
     marine
    0.44
    boxylic
    0.44
     acque
    0.44
    Activations Density 1.443%

    No Known Activations