© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10249
    Prev
    Next
    INDEX
    Explanations

    words that are often used when writing a scientific paper or abstract

    oai_token-act-pair · gemini-2.0-flash

    specific programming or technical terms

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

    Non-English words

    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
     sine
    -0.41
     Click
    -0.40
    дини
    -0.40
     ABSOL
    -0.38
    abd
    -0.37
    mozilla
    -0.37
     manos
    -0.36
    tas
    -0.36
    Klik
    -0.36
    getConfig
    -0.35
    POSITIVE LOGITS
     pinulongan
    0.99
    UnusedPrivate
    0.94
    ArrowToggle
    0.90
     يتيمه
    0.88
    InjectAttribute
    0.85
    +#+#
    0.84
    StoryboardSegue
    0.81
    Filmographie
    0.81
     OFDb
    0.80
     Wikimedijinoj
    0.78
    Activations Density 4.828%

    No Known Activations