© 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. 13005
    Prev
    Next
    INDEX
    Explanations

    scientific writing containing chemical or biological terms, particularly related to chemical reactions and amines, within a structured technical context.

    oai_token-act-pair · gemini-2.0-flash

    chemical processes

    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
     Référence
    -0.79
    CloseOperation
    -0.74
     récon
    -0.69
    GEBURTSDATUM
    -0.69
     auroit
    -0.68
     consultato
    -0.67
    setContentView
    -0.67
    TagHelpers
    -0.66
    HasAnnotation
    -0.66
    GraphicsUnit
    -0.66
    POSITIVE LOGITS
    MessageTagHelper
    0.52
    lig
    0.44
     ex
    0.44
    Tis
    0.42
    ex
    0.39
    aler
    0.36
     raw
    0.36
     por
    0.36
    ring
    0.35
    erve
    0.35
    Activations Density 4.111%

    No Known Activations