© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8543
    Prev
    Next
    INDEX
    Explanations

    mathematical texts talking about tensors, products and algebras

    oai_token-act-pair · gemini-2.0-flash

    product

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    RectangleBorder
    -1.09
     disambiguazione
    -0.97
     cherchés
    -0.95
     utafitiHapana
    -0.90
     дописавши
    -0.88
    RenderAtEndOf
    -0.85
    istoitu
    -0.85
    IGraphics
    -0.84
    хьтан
    -0.82
    SequentialGroup
    -0.82
    POSITIVE LOGITS
     Barn
    0.44
     enfo
    0.38
    null
    0.38
     law
    0.37
    Kaj
    0.36
     null
    0.36
    ̣ng
    0.36
     apro
    0.35
    Vak
    0.35
    咬
    0.35
    Activations Density 1.530%

    No Known Activations