© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11839
    Prev
    Next
    INDEX
    Explanations

    the prefix "De" in names

    oai_token-act-pair · gemini-2.0-flash

    De

    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
    мона
    -0.47
    ni
    -0.46
    wani
    -0.45
    annotation
    -0.42
    ini
    -0.42
    기도
    -0.42
    淡
    -0.42
     mimo
    -0.42
     van
    -0.41
    iorno
    -0.41
    POSITIVE LOGITS
    ConstraintMaker
    1.02
     فريبيس
    0.93
     nakalista
    0.91
     typelib
    0.85
     WaitForSeconds
    0.72
    Hauptartikel
    0.72
    AsUp
    0.71
     समीक्षाओं
    0.70
    ^(@)
    0.69
    Geplaatst
    0.68
    Activations Density 0.340%

    No Known Activations