© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13673
    Prev
    Next
    INDEX
    Explanations

    statistical comparisons and figures

    oai_token-act-pair · gemini-2.0-flash

    5

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    -0.61
    Parcelize
    -0.60
     createSprite
    -0.60
     onAnimation
    -0.58
     indisponible
    -0.54
     Odysseus
    -0.54
    IBarButtonItem
    -0.52
    ⓘ
    -0.52
    ihnachten
    -0.52
     AspNetCore
    -0.52
    POSITIVE LOGITS
     Paglinawan
    0.61
    ewon
    0.59
     Besøkt
    0.56
     traced
    0.50
    roux
    0.48
     trưởng
    0.47
     source
    0.46
     bra
    0.46
     Bra
    0.45
    leiter
    0.44
    Activations Density 26.208%

    No Known Activations