© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12680
    Prev
    Next
    INDEX
    Explanations

    references to public performance venues and the events that take place within them

    oai_token-act-pair · gemini-2.0-flash

    Events, maybe with crowds

    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
    SharedDtor
    -0.67
     '\\;'
    -0.66
    omitempty
    -0.61
     détermination
    -0.57
    WriteTagHelper
    -0.56
     manutenzione
    -0.56
     poignée
    -0.56
    retudo
    -0.55
     فريبيس
    -0.54
     photographie
    -0.54
    POSITIVE LOGITS
    Suara
    0.55
     RAC
    0.52
     ra
    0.51
    ⓘ
    0.50
    pédie
    0.47
    annica
    0.47
    netics
    0.47
    kuuta
    0.45
    cleros
    0.45
    entant
    0.45
    Activations Density 1.607%

    No Known Activations