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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6388
    Prev
    Next
    INDEX
    Explanations

    conjugation of present tense verbs

    oai_token-act-pair · gemini-2.0-flash

    special tokens or identifiers in code

    np_token-act-pair-logits · gpt-4o-mini

    Programming and foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     otomatig
    -0.65
    ACIAS
    -0.51
     wir
    -0.48
    adering
    -0.48
    BottomSheet
    -0.48
    principalColumn
    -0.47
    menuStrip
    -0.47
    UITableView
    -0.47
    писи
    -0.46
    fai
    -0.45
    POSITIVE LOGITS
    ون
    0.72
    وا
    0.64
    AndEndTag
    0.63
     verrez
    0.62
    jo
    0.61
    InjectAttribute
    0.60
    sidemargin
    0.60
    ją
    0.55
     Roskov
    0.54
    ViewImports
    0.53
    Activations Density 0.325%

    No Known Activations