© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10220
    Prev
    Next
    INDEX
    Explanations

    javascript code related to mouse clicks

    oai_token-act-pair · gemini-2.0-flash

    mouse input

    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
    WebVitals
    -0.48
    TagHelper
    -0.47
    reportWebVitals
    -0.47
     contribu
    -0.46
     contributions
    -0.46
    !';
    -0.46
     Италијани
    -0.46
    !',
    -0.46
    igi
    -0.45
    лая
    -0.45
    POSITIVE LOGITS
    Down
    0.61
     wireType
    0.58
    WriteTagHelper
    0.55
     Arhi
    0.55
     Taktlose
    0.54
     Himo
    0.53
    AYSIA
    0.51
    uxxxx
    0.51
    meuble
    0.50
    iettivo
    0.50
    Activations Density 1.168%

    No Known Activations