© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2298
    Prev
    Next
    INDEX
    Explanations

    fragmented and disparate coding languages and special characters, including math symbols, strings, and code syntax

    oai_token-act-pair · gemini-2.0-flash

    scientific/mathematical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     الرياضيه
    -0.57
    ReusableCell
    -0.55
    styleable
    -0.53
    #+#
    -0.52
    XmlAccessorType
    -0.51
    RectangleBorder
    -0.50
    Collegamenti
    -0.49
    onAttach
    -0.49
     AssemblyCulture
    -0.49
    propTypes
    -0.49
    POSITIVE LOGITS
    quelize
    0.65
    Notae
    0.63
    JMenuBar
    0.58
    WIT
    0.55
     Maja
    0.53
    envolvimento
    0.52
     NSError
    0.52
     Tenggara
    0.51
     Ond
    0.51
    Sae
    0.50
    Activations Density 11.963%

    No Known Activations