© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9882
    Prev
    Next
    INDEX
    Explanations

    words within a job listing or any document with requirements or steps.

    oai_token-act-pair · gemini-2.0-flash

    background

    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
    AndEndTag
    -0.69
    Hentet
    -0.66
    WriteAttribute
    -0.62
    RoutingModule
    -0.61
    <!--[
    -0.61
     مرئيه
    -0.61
    AspNetCore
    -0.59
    SuppressMessage
    -0.58
    ValueStyle
    -0.57
     surla
    -0.57
    POSITIVE LOGITS
     background
    1.50
     Background
    1.31
    Background
    1.20
    background
    1.20
     BACKGROUND
    1.11
    背景
    1.03
     backgrounds
    0.98
    BACKGROUND
    0.96
     Hintergrund
    0.90
     achtergrond
    0.83
    Activations Density 2.814%

    No Known Activations