© 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. 10530
    Prev
    Next
    INDEX
    Explanations

    various discourse markers, pronouns, and helping verbs.

    oai_token-act-pair · gemini-2.0-flash

    draw

    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
    ंदीखरीदारी
    -0.71
     disambiguazione
    -0.71
    Vanjske
    -0.63
    fjspx
    -0.59
    InputTagHelper
    -0.58
     GetEnumerator
    -0.57
    IUrlHelper
    -0.57
    Ծանոթ
    -0.56
     fopen
    -0.55
    UrlResolution
    -0.54
    POSITIVE LOGITS
     draw
    3.00
     drawing
    2.98
     draws
    2.75
     drawn
    2.69
     Drawing
    2.67
     drew
    2.63
     Draw
    2.55
    draw
    2.50
    Drawing
    2.45
    drawing
    2.45
    Activations Density 3.743%

    No Known Activations