© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5142
    Prev
    Next
    INDEX
    Explanations

    words relating to science and technology industries

    oai_token-act-pair · gemini-2.0-flash

    company/product descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     myſelf
    -1.09
     Jefus
    -1.05
    はじめに
    -0.95
     purpoſe
    -0.94
     Reſ
    -0.92
     Theſe
    -0.92
     Majefty
    -0.91
    ItemBackground
    -0.91
     Anſ
    -0.91
    yntaxException
    -0.90
    POSITIVE LOGITS
    uc
    0.47
    store
    0.45
    antMatchers
    0.43
     ca
    0.42
    cupa
    0.41
     Board
    0.41
     tắt
    0.40
     g
    0.39
     New
    0.39
     bas
    0.38
    Activations Density 1.654%

    No Known Activations