© 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. 12565
    Prev
    Next
    INDEX
    Explanations

    the letter "K" in references like [@...-K...]

    oai_token-act-pair · gemini-2.0-flash

    occurrences of the letter 'K'

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

    K

    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
     understatement
    -0.54
     Lancet
    -0.51
     modalités
    -0.50
    henswürdigkeiten
    -0.49
     récomp
    -0.49
    intéress
    -0.49
     fhew
    -0.49
    phem
    -0.48
     enjeux
    -0.48
     rius
    -0.48
    POSITIVE LOGITS
     ModelExpression
    0.61
     pinulongan
    0.56
    MessageTagHelper
    0.52
     PropertyChanged
    0.52
    ंदीखरीदारी
    0.51
    tagHelper
    0.50
    WEBPACK
    0.48
     ?>>
    0.47
     Վերցված
    0.46
    TagHelpers
    0.46
    Activations Density 0.219%

    No Known Activations