© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13291
    Prev
    Next
    INDEX
    Explanations

    proper nouns indicating people's names and titles

    oai_token-act-pair · gemini-2.0-flash

    technical jargon or terms related to computer programming

    np_token-act-pair-logits · gpt-4o-mini
    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
     а
    -0.52
     hendes
    -0.50
     degener
    -0.47
    secuencias
    -0.47
    quelle
    -0.46
    DebuggerStep
    -0.46
    BackStack
    -0.46
     suprême
    -0.43
     ashore
    -0.42
     כס
    -0.41
    POSITIVE LOGITS
    verwijspagina
    0.77
    sidemargin
    0.71
    ContentAsync
    0.69
    EndContext
    0.68
    MemoryWarning
    0.67
     CURIAM
    0.66
    queryInterface
    0.66
    HasAnnotation
    0.64
    LabelTagHelper
    0.63
    MENAFN
    0.63
    Activations Density 0.246%

    No Known Activations