© 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. 4325
    Prev
    Next
    INDEX
    Explanations

    various symbols, punctuation, and prepositions

    oai_token-act-pair · gemini-2.0-flash

    programming or coding terms

    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
     leben
    -0.51
     soutien
    -0.50
     članak
    -0.49
     BorderSide
    -0.48
    latego
    -0.47
     FetchType
    -0.47
     wohnen
    -0.47
     palavra
    -0.47
     indietro
    -0.47
     siège
    -0.47
    POSITIVE LOGITS
    PerformLayout
    0.65
     Audiodateien
    0.65
    rungsseite
    0.63
    inoa
    0.60
    Pyx
    0.58
     chi̍t
    0.57
    MessageTagHelper
    0.57
    TagHelpers
    0.56
    UnknownFieldSet
    0.56
    unia
    0.54
    Activations Density 0.600%

    No Known Activations