© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7721
    Prev
    Next
    INDEX
    Explanations

    language describing actions or events related to business management

    oai_token-act-pair · gemini-2.0-flash

    periods

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Awesome
    -0.51
    申し上げます
    -0.47
     still
    -0.45
     but
    -0.45
    ่าง
    -0.44
     Great
    -0.44
     yes
    -0.43
    still
    -0.43
    pagestyle
    -0.42
     glad
    -0.42
    POSITIVE LOGITS
    setVerticalGroup
    0.77
    tagHelperRunner
    0.72
    SequentialGroup
    0.71
    AndEndTag
    0.71
     CreateTagHelper
    0.69
    +:+
    0.66
    المشاركات
    0.63
    complexContent
    0.62
    adaptiveStyles
    0.62
    Bibliograf
    0.60
    Activations Density 1.903%

    No Known Activations