© 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. 4867
    Prev
    Next
    INDEX
    Explanations

    documentation about software packages related to databases

    oai_token-act-pair · gemini-2.0-flash

    Software features and libraries

    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
     للمعارف
    -0.53
    IUrlHelper
    -0.49
    adpleegd
    -0.49
    ValueGenerated
    -0.48
     linkovi
    -0.48
    AsUp
    -0.47
    exitRule
    -0.47
    upport
    -0.47
    harma
    -0.46
     support
    -0.45
    POSITIVE LOGITS
     оригіналу
    0.62
    TargetException
    0.58
    δά
    0.54
    MENAFN
    0.54
     separates
    0.54
    XmlAccessType
    0.53
     tartalomajánló
    0.52
     Queries
    0.52
     calculates
    0.51
    cila
    0.50
    Activations Density 8.258%

    No Known Activations