© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10838
    Prev
    Next
    INDEX
    Explanations

    text discussing increases

    oai_token-act-pair · gemini-2.0-flash

    words related to levels or increases

    np_token-act-pair-logits · gpt-4o-mini

    increasing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    Obrázky
    -0.50
    @[+][
    -0.47
     javafx
    -0.45
     Waray
    -0.45
     iconst
    -0.44
     Lightboxes
    -0.43
     "}";
    -0.43
     Paglinawan
    -0.42
     naturels
    -0.42
     weinig
    -0.42
    POSITIVE LOGITS
     level
    0.65
     levels
    0.63
     LEVEL
    0.60
     Level
    0.59
    ThroughAttribute
    0.58
     Levels
    0.57
     prevalence
    0.56
     LEVELS
    0.56
    levels
    0.56
    level
    0.56
    Activations Density 4.516%

    No Known Activations