© 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. 5246
    Prev
    Next
    INDEX
    Explanations

    statistics and numerical data

    oai_token-act-pair · gemini-2.0-flash

    period

    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
    kwds
    -0.50
     litro
    -0.47
     téléphonique
    -0.47
     Conci
    -0.45
     sementara
    -0.45
     Quiero
    -0.44
     Seriously
    -0.44
     Mann
    -0.43
     mittler
    -0.43
     helft
    -0.43
    POSITIVE LOGITS
    MENAFN
    0.71
     NgModule
    0.68
    IContainer
    0.67
    UserScript
    0.64
    tagHelperRunner
    0.60
    chwitz
    0.58
     Wicidata
    0.58
    richTextPanel
    0.57
     initComponents
    0.57
    /***/
    0.57
    Activations Density 3.827%

    No Known Activations