© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5037
    Prev
    Next
    INDEX
    Explanations

    code snippets with variable assignments and references to fields or objects

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     disambiguazione
    -1.24
     betweenstory
    -1.23
    afficheront
    -1.22
    Personensuche
    -1.21
     الحره
    -1.20
    expandindo
    -1.20
    Personendaten
    -1.20
    WebVitals
    -1.16
    ंदीखरीदारी
    -1.15
    Хьажоргаш
    -1.14
    POSITIVE LOGITS
    ,
    1.01
     
    0.63
    ↵
    0.60
    .,
    0.52
     ,
    0.52
     d
    0.51
     D
    0.47
    ，
    0.45
     in
    0.44
     n
    0.44
    Activations Density 3.409%

    No Known Activations