© 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. 5048
    Prev
    Next
    INDEX
    Explanations

    the letter i followed by numbers, along with related programming terms such as flags, mode, len, and d

    oai_token-act-pair · gemini-2.0-flash

    identifiers in code

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

    say "brackets"

    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
     AssemblyCulture
    -0.83
    ⓧ
    -0.69
    thâu
    -0.65
    +#+#
    -0.57
    KommentareTeilen
    -0.56
    Diwedd
    -0.56
    culin
    -0.55
    GraphicsUnit
    -0.54
    autorest
    -0.54
     transférez
    -0.52
    POSITIVE LOGITS
    matchCondition
    0.57
    HasForeignKey
    0.55
    prefixer
    0.52
    couvrez
    0.52
     protoimpl
    0.51
    elfare
    0.51
    SqlClient
    0.50
    uitton
    0.50
     onBackPressed
    0.49
    landet
    0.49
    Activations Density 2.514%

    No Known Activations